{"models":[{"id":"deepseek/deepseek-v4.1-flash-1017","slug":"deepseek-v4-1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","provider":"deepseek","contextLength":1048576,"pricing":{"inputPerM":0.15,"outputPerM":0.6},"releasedAt":"2026-10-17","huggingFaceId":"deepseek-ai/DeepSeek-V4.1-Flash-1017","profile":{"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...","inputModalities":["text","image"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":393216,"knowledgeCutoff":null,"cacheReadPerM":0.003,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"DeepSeek","moderated":false,"expiresAt":null,"canonicalSlug":"deepseek/deepseek-v4.1-flash-20261017"}},{"id":"elorian/glimpse","slug":"elorian-glimpse","name":"Elorian: Glimpse","provider":"elorian","contextLength":262144,"pricing":{"inputPerM":0.6,"outputPerM":3},"releasedAt":"2026-10-17","huggingFaceId":null,"profile":{"description":"Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world. It reasons directly over images and video rather than...","inputModalities":["text","image","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":256000,"knowledgeCutoff":null,"cacheReadPerM":0.06,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"elorian/glimpse-20261016"}},{"id":"reflection/beam-1.0-501b-a23b","slug":"reflection-beam-1-0-501b-a23b","name":"Reflection: Beam 1.0 501B A23B","provider":"reflection","contextLength":1048576,"pricing":{"inputPerM":0.3,"outputPerM":1},"releasedAt":"2026-10-16","huggingFaceId":"reflection/Beam-1.0-501B-A23B","profile":{"description":"Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":943718,"knowledgeCutoff":"2026-06-30","cacheReadPerM":0.04,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"reflection/beam-1.0-501b-a23b-20261016"}},{"id":"inception/mercury-3","slug":"inception-mercury-3","name":"Inception: Mercury 3","provider":"inception","contextLength":1000000,"pricing":{"inputPerM":0.1,"outputPerM":0.35},"releasedAt":"2026-10-16","huggingFaceId":null,"profile":{"description":"Mercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date. It is suited for agentic workflows and real-time applications where latency compounds, such...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":131072,"knowledgeCutoff":null,"cacheReadPerM":0.01,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"inception/mercury-3-20261019"}},{"id":"moondream/moondream3-preview","slug":"moondream-moondream3-preview","name":"Moondream: Moondream 3 Preview","provider":"moondream","contextLength":32000,"pricing":{"inputPerM":0.3,"outputPerM":2.5},"releasedAt":"2026-10-15","huggingFaceId":"moondream/moondream3-preview","profile":{"description":"Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with...","inputModalities":["text","image"],"outputModalities":["text"],"features":["reasoning"],"maxOutput":4096,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"moondream/moondream3-preview-20261013"}},{"id":"moondream/moondream3.1-9b-a2b","slug":"moondream-moondream3-1-9b-a2b","name":"Moondream: Moondream 3.1","provider":"moondream","contextLength":32000,"pricing":{"inputPerM":0.3,"outputPerM":2.5},"releasedAt":"2026-10-15","huggingFaceId":"moondream/moondream3.1-9B-A2B","profile":{"description":"Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and...","inputModalities":["text","image"],"outputModalities":["text"],"features":["reasoning"],"maxOutput":4096,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"moondream/moondream3.1-9b-a2b-20261013"}},{"id":"meta/muse-spark-open","slug":"meta-muse-spark-open","name":"Meta: Muse Spark Open","provider":"meta","contextLength":1048576,"pricing":{"inputPerM":1.25,"outputPerM":4.25},"releasedAt":"2026-10-15","huggingFaceId":"meta-models/Muse-Spark-Open-816B-A42B","profile":{"description":"Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers...","inputModalities":["text","image","video","file","audio"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":943718,"knowledgeCutoff":null,"cacheReadPerM":0.15,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"meta/muse-spark-open-20261015"}},{"id":"nvidia/nemotron-3.5-super-vl","slug":"nvidia-nemotron-3-5-super-vl","name":"NVIDIA: Nemotron 3.5 Super VL","provider":"nvidia","contextLength":1048576,"pricing":{"inputPerM":0.15,"outputPerM":0.5},"releasedAt":"2026-10-15","huggingFaceId":"nvidia/NVIDIA-Nemotron-3.5-Super-VL","profile":{"description":"NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...","inputModalities":["text","image","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":235929,"knowledgeCutoff":null,"cacheReadPerM":0.02,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"nvidia/nemotron-3.5-super-vl-20261015"}},{"id":"unbiased/pareto-26.10","slug":"unbiased-pareto-26-10","name":"Pareto 26.10","provider":"unbiased","contextLength":1048576,"pricing":{"inputPerM":0.8,"outputPerM":3.2},"releasedAt":"2026-10-15","huggingFaceId":null,"profile":{"description":"Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.","inputModalities":["text","image"],"outputModalities":["text"],"features":["tools"],"maxOutput":131072,"knowledgeCutoff":null,"cacheReadPerM":0.03,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"unbiased/pareto-26.10-20261015"}},{"id":"unbiased/pareto-26.9","slug":"unbiased-pareto-26-9","name":"Pareto 26.9","provider":"unbiased","contextLength":262144,"pricing":{"inputPerM":2.5,"outputPerM":7.5},"releasedAt":"2026-10-13","huggingFaceId":null,"profile":{"description":"Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.","inputModalities":["text","image"],"outputModalities":["text"],"features":["json-mode","tools"],"maxOutput":131072,"knowledgeCutoff":null,"cacheReadPerM":0.25,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"unbiased/pareto-26.9-20260917"}},{"id":"liquid/lfm-2.5-24b-a2b","slug":"liquid-lfm-2-5-24b-a2b","name":"LiquidAI: LFM2.5-24B-A2B","provider":"liquid","contextLength":128000,"pricing":{"inputPerM":0.05,"outputPerM":0.7},"releasedAt":"2026-10-13","huggingFaceId":"LiquidAI/LFM2.5-24B-A2B","profile":{"description":"LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":8192,"knowledgeCutoff":null,"cacheReadPerM":0.025,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"liquid/lfm-2.5-24b-a2b-20261012"}},{"id":"google/gemini-4-argon","slug":"gemini-4-argon","name":"Google: Gemini 4 Argon","provider":"google","contextLength":1048576,"pricing":{"inputPerM":2,"outputPerM":10},"releasedAt":"2026-10-13","huggingFaceId":null,"profile":{"description":"Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...","inputModalities":["audio","file","image","text","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":943718,"knowledgeCutoff":null,"cacheReadPerM":0.1,"cacheWritePerM":0.1875,"reasoningPerM":10,"webSearchPerRequest":0.014,"tokenizer":"Gemini","moderated":false,"expiresAt":null,"canonicalSlug":"google/gemini-4-argon-20261013"}},{"id":"scaledown/summarize","slug":"scaledown-summarize","name":"ScaleDown: Summarize","provider":"scaledown","contextLength":1000000,"pricing":{"inputPerM":0.04,"outputPerM":0},"releasedAt":"2026-10-13","huggingFaceId":null,"profile":{"description":"Summarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifting sentences from the source, and is suited for...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":[],"maxOutput":4000,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"scaledown/summarize-20260928"}},{"id":"scaledown/extract","slug":"scaledown-extract","name":"ScaleDown: Extract","provider":"scaledown","contextLength":1000000,"pricing":{"inputPerM":0.04,"outputPerM":0},"releasedAt":"2026-10-13","huggingFaceId":null,"profile":{"description":"Extract is a description-driven entity extraction model from ScaleDown. Instead of a fixed set of entity types, callers describe the fields they want in plain English through `provider.options.scaledown.entities`, and the...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":[],"maxOutput":900000,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"scaledown/extract-20260928"}},{"id":"meta/muse-wonder","slug":"meta-muse-wonder","name":"Meta: Muse Wonder","provider":"meta","contextLength":1048576,"pricing":{"inputPerM":4,"outputPerM":20},"releasedAt":"2026-10-12","huggingFaceId":null,"profile":{"description":"Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with...","inputModalities":["text","image","video","file","audio"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":943718,"knowledgeCutoff":null,"cacheReadPerM":0.2,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.0025,"tokenizer":null,"moderated":true,"expiresAt":null,"canonicalSlug":"meta/muse-wonder-20261012"}},{"id":"stepfun/step-5-preview","slug":"stepfun-step-5-preview","name":"StepFun: Step 5 Preview","provider":"stepfun","contextLength":1048576,"pricing":{"inputPerM":1,"outputPerM":2.7},"releasedAt":"2026-10-08","huggingFaceId":"stepfun-ai/Step-5-Preview","profile":{"description":"Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional...","inputModalities":["text","image","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":64000,"knowledgeCutoff":null,"cacheReadPerM":0.1,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"stepfun/step-5-preview-20261008"}},{"id":"anthropic/claude-haiku-5.5","slug":"claude-haiku-5-5","name":"Anthropic: Claude Haiku 5.5","provider":"anthropic","contextLength":1000000,"pricing":{"inputPerM":0.1,"outputPerM":0.5},"releasedAt":"2026-10-07","huggingFaceId":null,"profile":{"description":"Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2026-06","cacheReadPerM":0.01,"cacheWritePerM":0.125,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"Claude","moderated":true,"expiresAt":null,"canonicalSlug":"anthropic/claude-haiku-5.5-20261007","knowledgeCutoffSource":{"label":"Anthropic model documentation","url":"https://platform.claude.com/docs/en/models/haiku-5-5/overview.md"}}},{"id":"google/gemini-nano-banana-2.1","slug":"gemini-nano-banana-2-1","name":"Google: Nano Banana 2.1","provider":"google","contextLength":65536,"pricing":{"inputPerM":1.5,"outputPerM":7.5},"releasedAt":"2026-10-06","huggingFaceId":null,"profile":{"description":"Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization,...","inputModalities":["image","text"],"outputModalities":["image","text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":58982,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.014,"tokenizer":"Gemini","moderated":false,"expiresAt":null,"canonicalSlug":"google/gemini-nano-banana-2.1-20261006"}},{"id":"mistralai/mistral-large-4-0","slug":"mistral-large-4-0","name":"Mistral: Mistral Large 4","provider":"mistralai","contextLength":1048576,"pricing":{"inputPerM":0.68,"outputPerM":2.09},"releasedAt":"2026-10-06","huggingFaceId":null,"profile":{"description":"Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up...","inputModalities":["text","image"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":262144,"knowledgeCutoff":null,"cacheReadPerM":0.07,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Mistral","moderated":false,"expiresAt":null,"canonicalSlug":"mistralai/mistral-large-4-0-20261006"}},{"id":"inclusionai/ling-3.1-flash","slug":"inclusionai-ling-3-1-flash","name":"inclusionAI: Ling 3.1 Flash","provider":"inclusionai","contextLength":262144,"pricing":{"inputPerM":0.075,"outputPerM":0.225},"releasedAt":"2026-10-02","huggingFaceId":null,"profile":{"description":"Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":235929,"knowledgeCutoff":null,"cacheReadPerM":0.015,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"inclusionai/ling-3.1-flash-20261002"}},{"id":"openai/gpt-6.1-sol-pro","slug":"gpt-6-1-sol-pro","name":"OpenAI: GPT-6.1 Sol Pro","provider":"openai","contextLength":1050000,"pricing":{"inputPerM":2,"outputPerM":10},"releasedAt":"2026-09-29","huggingFaceId":null,"profile":{"description":"GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","inputModalities":["file","image","text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":null,"cacheReadPerM":0.1,"cacheWritePerM":2.5,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-6.1-sol-pro-20260929"}},{"id":"openai/gpt-6.1-sol","slug":"gpt-6-1-sol","name":"OpenAI: GPT-6.1 Sol","provider":"openai","contextLength":1050000,"pricing":{"inputPerM":2,"outputPerM":10},"releasedAt":"2026-09-29","huggingFaceId":null,"profile":{"description":"GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional...","inputModalities":["file","image","text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2026-04-30","cacheReadPerM":0.1,"cacheWritePerM":2.5,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-6.1-sol-20260929","knowledgeCutoffSource":{"label":"OpenAI model documentation","url":"https://developers.openai.com/api/docs/models/gpt-6.1-sol.md"}}},{"id":"anthropic/claude-sonnet-5.5","slug":"claude-sonnet-5-5","name":"Anthropic: Claude Sonnet 5.5","provider":"anthropic","contextLength":1000000,"pricing":{"inputPerM":2,"outputPerM":10},"releasedAt":"2026-09-28","huggingFaceId":null,"profile":{"description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2026-06","cacheReadPerM":0.1,"cacheWritePerM":2.5,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"Claude","moderated":false,"expiresAt":null,"canonicalSlug":"anthropic/claude-sonnet-5.5-20260928","knowledgeCutoffSource":{"label":"Anthropic model documentation","url":"https://platform.claude.com/docs/en/models/sonnet-5-5/overview.md"}}},{"id":"typesafe/jev-router","slug":"typesafe-jev-router","name":"TypeSafe: Jev Router","provider":"typesafe","contextLength":1000000,"pricing":null,"releasedAt":"2026-09-25","huggingFaceId":null,"profile":{"description":"Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost. It runs on [Jev](https://openrouter.ai/~typesafe/jev-latest), TypeSafe's first System One model, and adapts as your...","inputModalities":["audio","file","image","text","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":null,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Router","moderated":false,"expiresAt":null,"canonicalSlug":"typesafe/jev-router"}},{"id":"perceptron/perceptron-mk1.5","slug":"perceptron-perceptron-mk1-5","name":"Perceptron: Perceptron Mk1.5","provider":"perceptron","contextLength":36864,"pricing":{"inputPerM":0.15,"outputPerM":1.5},"releasedAt":"2026-09-25","huggingFaceId":null,"profile":{"description":"Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optional structured annotations: points, boxes, polygons, tracks,...","inputModalities":["text","image","video","audio"],"outputModalities":["text"],"features":["reasoning","structured-outputs","tools"],"maxOutput":8192,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"perceptron/perceptron-mk1.5-20260925"}},{"id":"fireworks/ember-1","slug":"fireworks-ember-1","name":"Fireworks: Ember-1","provider":"fireworks","contextLength":1048576,"pricing":{"inputPerM":3,"outputPerM":15},"releasedAt":"2026-09-24","huggingFaceId":null,"profile":{"description":"Ember-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3](https://openrouter.ai/moonshotai/kimi-k3). It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40%...","inputModalities":["text","image"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":943718,"knowledgeCutoff":null,"cacheReadPerM":0.3,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"fireworks/ember-1-20260923"}},{"id":"z-ai/glm-5.3-prime","slug":"glm-5-3-prime","name":"Z.ai: GLM 5.3 Prime","provider":"z-ai","contextLength":1000000,"pricing":{"inputPerM":2.8,"outputPerM":8.8},"releasedAt":"2026-09-23","huggingFaceId":null,"profile":{"description":"GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5, 2× the output throughput through inference acceleration. It supports text input and output with a 1M-token...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","tools"],"maxOutput":131072,"knowledgeCutoff":null,"cacheReadPerM":0.56,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"z-ai/glm-5.3-prime-20260921"}},{"id":"qwen/qwen3.8-max-prime","slug":"qwen3-8-max-prime","name":"Qwen: Qwen3.8 Max Prime","provider":"qwen","contextLength":1000000,"pricing":{"inputPerM":4,"outputPerM":12},"releasedAt":"2026-09-23","huggingFaceId":null,"profile":{"description":"Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video...","inputModalities":["text","image","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":131072,"knowledgeCutoff":null,"cacheReadPerM":0.5,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3.8-max-prime-20260923"}},{"id":"aion-labs/aion-3.5-mini","slug":"aion-labs-aion-3-5-mini","name":"AionLabs: Aion 3.5 Mini","provider":"aion-labs","contextLength":262144,"pricing":{"inputPerM":0.7,"outputPerM":1.4},"releasedAt":"2026-09-23","huggingFaceId":null,"profile":{"description":"Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It is the smaller, lower-cost sibling of Aion 3.5 and uses...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","tools"],"maxOutput":32768,"knowledgeCutoff":null,"cacheReadPerM":0.18,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"aion-labs/aion-3.5-mini-20260923"}},{"id":"aion-labs/aion-3.5","slug":"aion-labs-aion-3-5","name":"AionLabs: Aion 3.5","provider":"aion-labs","contextLength":262144,"pricing":{"inputPerM":3,"outputPerM":6},"releasedAt":"2026-09-23","huggingFaceId":null,"profile":{"description":"Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","tools"],"maxOutput":32768,"knowledgeCutoff":null,"cacheReadPerM":0.75,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"aion-labs/aion-3.5-20260923"}},{"id":"upstage/solar-mini4","slug":"upstage-solar-mini4","name":"Upstage: Solar Mini 4","provider":"upstage","contextLength":524288,"pricing":{"inputPerM":0.05,"outputPerM":0.2},"releasedAt":"2026-09-23","huggingFaceId":null,"profile":{"description":"Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window. It is built for agentic use cases where response...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":131072,"knowledgeCutoff":null,"cacheReadPerM":0.005,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"upstage/solar-mini4-20260922"}},{"id":"cohere/command-a-plus","slug":"cohere-command-a-plus","name":"Cohere: Command A+","provider":"cohere","contextLength":192000,"pricing":{"inputPerM":0.3,"outputPerM":1.5},"releasedAt":"2026-09-22","huggingFaceId":null,"profile":{"description":"Command A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports native tool calling with strict tool schemas, structured...","inputModalities":["text","image"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":64000,"knowledgeCutoff":null,"cacheReadPerM":0.15,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Cohere","moderated":true,"expiresAt":null,"canonicalSlug":"cohere/command-a-plus-05-2026"}},{"id":"openai/gpt-6-luna-pro","slug":"gpt-6-luna-pro","name":"OpenAI: GPT-6 Luna Pro","provider":"openai","contextLength":1050000,"pricing":{"inputPerM":0.1,"outputPerM":0.5},"releasedAt":"2026-09-22","huggingFaceId":null,"profile":{"description":"GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","inputModalities":["file","image","text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":null,"cacheReadPerM":0.01,"cacheWritePerM":0.125,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-6-luna-pro-20260922"}},{"id":"openai/gpt-6-luna","slug":"gpt-6-luna","name":"OpenAI: GPT-6 Luna","provider":"openai","contextLength":1050000,"pricing":{"inputPerM":0.1,"outputPerM":0.5},"releasedAt":"2026-09-22","huggingFaceId":null,"profile":{"description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...","inputModalities":["file","image","text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2026-05-18","cacheReadPerM":0.01,"cacheWritePerM":0.125,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-6-luna-20260922","knowledgeCutoffSource":{"label":"OpenAI model documentation","url":"https://developers.openai.com/api/docs/models/gpt-6-luna.md"}}},{"id":"openai/gpt-6-sol-pro","slug":"gpt-6-sol-pro","name":"OpenAI: GPT-6 Sol Pro","provider":"openai","contextLength":1050000,"pricing":{"inputPerM":2,"outputPerM":10},"releasedAt":"2026-09-22","huggingFaceId":null,"profile":{"description":"GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","inputModalities":["file","image","text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":null,"cacheReadPerM":0.2,"cacheWritePerM":2.5,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-6-sol-pro-20260922"}},{"id":"openai/gpt-6-sol","slug":"gpt-6-sol","name":"OpenAI: GPT-6 Sol","provider":"openai","contextLength":1050000,"pricing":{"inputPerM":2,"outputPerM":10},"releasedAt":"2026-09-22","huggingFaceId":null,"profile":{"description":"GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional...","inputModalities":["file","image","text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2026-04-20","cacheReadPerM":0.2,"cacheWritePerM":2.5,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-6-sol-20260922","knowledgeCutoffSource":{"label":"OpenAI model documentation","url":"https://developers.openai.com/api/docs/models/gpt-6-sol.md"}}},{"id":"anthropic/claude-opus-5.5","slug":"claude-opus-5-5","name":"Anthropic: Claude Opus 5.5","provider":"anthropic","contextLength":1000000,"pricing":{"inputPerM":4,"outputPerM":20},"releasedAt":"2026-09-22","huggingFaceId":null,"profile":{"description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2026-06","cacheReadPerM":0.2,"cacheWritePerM":5,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"Claude","moderated":true,"expiresAt":null,"canonicalSlug":"anthropic/claude-opus-5.5-20260921","knowledgeCutoffSource":{"label":"Anthropic model documentation","url":"https://platform.claude.com/docs/en/models/opus-5-5/overview.md"}}},{"id":"nvidia/switchyard","slug":"nvidia-switchyard","name":"NVIDIA: Switchyard","provider":"nvidia","contextLength":1000000,"pricing":null,"releasedAt":"2026-09-21","huggingFaceId":null,"profile":{"description":"Switchyard is an open-source model router that switches between multiple models to optimize the cost of requests. By default it will use OpenRouter market data to select the most popular...","inputModalities":["text"],"outputModalities":["text"],"features":[],"maxOutput":null,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Router","moderated":false,"expiresAt":null,"canonicalSlug":"nvidia/switchyard"}},{"id":"xiaomi/mimo-v2.6-pro-ultraspeed","slug":"xiaomi-mimo-v2-6-pro-ultraspeed","name":"Xiaomi: MiMo-V2.6-Pro-UltraSpeed","provider":"xiaomi","contextLength":1048576,"pricing":{"inputPerM":4.35,"outputPerM":8.7},"releasedAt":"2026-09-21","huggingFaceId":null,"profile":{"description":"MiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship foundation model, MiMo-V2.6-Pro. Built from the same 1T MiMo-V2.6-Pro checkpoint, it matches the original model in quality while delivering roughly 10x...","inputModalities":["text","image","video","audio"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":131072,"knowledgeCutoff":null,"cacheReadPerM":0.036,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"xiaomi/mimo-v2.6-pro-ultraspeed-20260921"}},{"id":"xiaomi/mimo-v2.6-flash","slug":"xiaomi-mimo-v2-6-flash","name":"Xiaomi: MiMo-V2.6-Flash","provider":"xiaomi","contextLength":1050000,"pricing":{"inputPerM":0.14,"outputPerM":0.28},"releasedAt":"2026-09-21","huggingFaceId":"XiaomiMiMo/MiMo-V2.6-Flash-RL","profile":{"description":"MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for...","inputModalities":["text","image","video","audio"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":131072,"knowledgeCutoff":null,"cacheReadPerM":0.0028,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"xiaomi/mimo-v2.6-flash-20260921"}},{"id":"xiaomi/mimo-v2.6-pro","slug":"xiaomi-mimo-v2-6-pro","name":"Xiaomi: MiMo-V2.6-Pro","provider":"xiaomi","contextLength":1050000,"pricing":{"inputPerM":0.435,"outputPerM":0.87},"releasedAt":"2026-09-21","huggingFaceId":"XiaomiMiMo/MiMo-V2.6-Pro-RL","profile":{"description":"MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding...","inputModalities":["text","image","video","audio"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":131072,"knowledgeCutoff":null,"cacheReadPerM":0.0036,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"xiaomi/mimo-v2.6-pro-20260921"}},{"id":"x-ai/grok-4.7","slug":"grok-4-7","name":"SpaceXAI: Grok 4.7","provider":"x-ai","contextLength":500000,"pricing":{"inputPerM":2,"outputPerM":6},"releasedAt":"2026-09-21","huggingFaceId":null,"profile":{"description":"Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":450000,"knowledgeCutoff":null,"cacheReadPerM":0.5,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.005,"tokenizer":"Grok","moderated":false,"expiresAt":null,"canonicalSlug":"x-ai/grok-4.7-20260916"}},{"id":"qwen/qwen3.8-omni-flash","slug":"qwen3-8-omni-flash","name":"Qwen: Qwen3.8 Omni Flash","provider":"qwen","contextLength":1000000,"pricing":{"inputPerM":0.15,"outputPerM":0.47},"releasedAt":"2026-09-21","huggingFaceId":null,"profile":{"description":"Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,...","inputModalities":["text","image","audio","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":131072,"knowledgeCutoff":null,"cacheReadPerM":0.016,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3.8-omni-flash-20260918"}},{"id":"prism-ml/ternary-bonsai-2-27b","slug":"prism-ml-ternary-bonsai-2-27b","name":"PrismML: Ternary Bonsai 2 27B","provider":"prism-ml","contextLength":262144,"pricing":{"inputPerM":0.075,"outputPerM":0.5},"releasedAt":"2026-09-18","huggingFaceId":"prism-ml/Ternary-Bonsai-2-27B-gguf","profile":{"description":"Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window. Ternary compression shrinks...","inputModalities":["text","image"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":32768,"knowledgeCutoff":null,"cacheReadPerM":0.0375,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen","moderated":false,"expiresAt":null,"canonicalSlug":"prism-ml/ternary-bonsai-2-27b-20260918"}},{"id":"z-ai/glm-5.3-flashx","slug":"glm-5-3-flashx","name":"Z.ai: GLM 5.3 FlashX","provider":"z-ai","contextLength":1048576,"pricing":{"inputPerM":0.37,"outputPerM":1.25},"releasedAt":"2026-09-18","huggingFaceId":null,"profile":{"description":"GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture...","inputModalities":["text","image","video"],"outputModalities":["text"],"features":["reasoning","json-mode","tools"],"maxOutput":131072,"knowledgeCutoff":null,"cacheReadPerM":0.09,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"z-ai/glm-5.3-flashx-20260918"}},{"id":"inference-net/schematron-v2-turbo","slug":"inference-net-schematron-v2-turbo","name":"Inference.net: Schematron V2 Turbo","provider":"inference-net","contextLength":128000,"pricing":{"inputPerM":0.03,"outputPerM":0.15},"releasedAt":"2026-09-12","huggingFaceId":"inference-net/schematron-v2-granite-4.0-h-micro","profile":{"description":"Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. Extraction instructions must be supplied through a JSON schema in response_format rather...","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs"],"maxOutput":8192,"knowledgeCutoff":null,"cacheReadPerM":0.03,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"inference-net/schematron-v2-turbo-20260902"}},{"id":"inference-net/schematron-v2-small","slug":"inference-net-schematron-v2-small","name":"Inference.net: Schematron V2 Small","provider":"inference-net","contextLength":128000,"pricing":{"inputPerM":0.05,"outputPerM":0.23},"releasedAt":"2026-09-12","huggingFaceId":"inference-net/schematron-v2-llama-3.2-3b","profile":{"description":"Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages. Extraction instructions must be supplied through a JSON schema...","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs"],"maxOutput":4096,"knowledgeCutoff":null,"cacheReadPerM":0.05,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"inference-net/schematron-v2-small-20260902"}},{"id":"sakana/fugu-ultra-v2","slug":"sakana-fugu-ultra-v2","name":"Sakana: Fugu Ultra v2","provider":"sakana","contextLength":1000000,"pricing":{"inputPerM":5,"outputPerM":30},"releasedAt":"2026-09-11","huggingFaceId":null,"profile":{"description":"Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["reasoning","structured-outputs","tools","web-search"],"maxOutput":128000,"knowledgeCutoff":"2026-08-28","cacheReadPerM":0.5,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"sakana/fugu-ultra-v2-20260911"}},{"id":"sakana/fugu-max","slug":"sakana-fugu-max","name":"Sakana: Fugu Max","provider":"sakana","contextLength":1000000,"pricing":{"inputPerM":2,"outputPerM":6},"releasedAt":"2026-09-11","huggingFaceId":null,"profile":{"description":"Fugu Max is the cost-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["reasoning","structured-outputs","tools","web-search"],"maxOutput":128000,"knowledgeCutoff":null,"cacheReadPerM":0.25,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"sakana/fugu-max-20260911"}},{"id":"inclusionai/ling-3.0-flash-vl","slug":"inclusionai-ling-3-0-flash-vl","name":"inclusionAI: Ling 3.0 Flash VL","provider":"inclusionai","contextLength":131072,"pricing":{"inputPerM":0.06,"outputPerM":0.18},"releasedAt":"2026-09-10","huggingFaceId":"inclusionAI/Ling-3.0-flash-VL","profile":{"description":"Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception and advanced visual...","inputModalities":["text","image","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":32768,"knowledgeCutoff":null,"cacheReadPerM":0.012,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"inclusionai/ling-3.0-flash-vl-20260910"}},{"id":"deepseek/deepseek-v4.1-flash","slug":"deepseek-v4-1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","provider":"deepseek","contextLength":1048576,"pricing":{"inputPerM":0.0352,"outputPerM":0.0112},"releasedAt":"2026-09-10","huggingFaceId":"deepseek-ai/DeepSeek-V4.1-Flash","profile":{"description":"DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...","inputModalities":["text","image"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":943718,"knowledgeCutoff":null,"cacheReadPerM":0.0016,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"DeepSeek","moderated":false,"expiresAt":null,"canonicalSlug":"deepseek/deepseek-v4.1-flash-20260910"}},{"id":"inception/mercury-2.5","slug":"inception-mercury-2-5","name":"Inception: Mercury 2.5","provider":"inception","contextLength":260000,"pricing":{"inputPerM":0.04,"outputPerM":0.15},"releasedAt":"2026-09-08","huggingFaceId":null,"profile":{"description":"Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":65536,"knowledgeCutoff":null,"cacheReadPerM":0.004,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"inception/mercury-2.5-20260908"}},{"id":"nex-agi/nex-n2.5-mini","slug":"nex-agi-nex-n2-5-mini","name":"Nex AGI: Nex-N2.5-Mini","provider":"nex-agi","contextLength":262144,"pricing":{"inputPerM":0.025,"outputPerM":0.1},"releasedAt":"2026-09-08","huggingFaceId":"nex-agi/Nex-N2.5-mini","profile":{"description":"Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...","inputModalities":["text","image"],"outputModalities":["text"],"features":["reasoning","structured-outputs"],"maxOutput":235929,"knowledgeCutoff":null,"cacheReadPerM":0.0025,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen3","moderated":false,"expiresAt":null,"canonicalSlug":"nex-agi/nex-n2.5-mini-20260908"}},{"id":"nex-agi/nex-n2.5-pro","slug":"nex-agi-nex-n2-5-pro","name":"Nex AGI: Nex-N2.5-Pro","provider":"nex-agi","contextLength":262144,"pricing":{"inputPerM":0.075,"outputPerM":0.25},"releasedAt":"2026-09-08","huggingFaceId":"nex-agi/Nex-N2.5-Pro","profile":{"description":"Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...","inputModalities":["text","image"],"outputModalities":["text"],"features":["reasoning","structured-outputs","tools"],"maxOutput":235929,"knowledgeCutoff":null,"cacheReadPerM":0.015,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen3","moderated":false,"expiresAt":null,"canonicalSlug":"nex-agi/nex-n2.5-pro-20260907"}},{"id":"openai/gpt-6-astra","slug":"gpt-6-astra","name":"OpenAI: GPT-6 Astra","provider":"openai","contextLength":1050000,"pricing":{"inputPerM":10,"outputPerM":50},"releasedAt":"2026-09-04","huggingFaceId":null,"profile":{"description":"GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...","inputModalities":["file","image","text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2026-04-30","cacheReadPerM":1,"cacheWritePerM":12.5,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-6-astra-20260903","knowledgeCutoffSource":{"label":"OpenAI model documentation","url":"https://developers.openai.com/api/docs/models/gpt-6-astra.md"}}},{"id":"openai/gpt-6-astra-pro","slug":"gpt-6-astra-pro","name":"OpenAI: GPT-6 Astra Pro","provider":"openai","contextLength":1050000,"pricing":{"inputPerM":10,"outputPerM":50},"releasedAt":"2026-09-04","huggingFaceId":null,"profile":{"description":"GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","inputModalities":["file","image","text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":null,"cacheReadPerM":1,"cacheWritePerM":12.5,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-6-astra-pro-20260903"}},{"id":"qwen/qwen3.8-max-0902","slug":"qwen3-8-max-0902","name":"Qwen: Qwen3.8 Max (0902)","provider":"qwen","contextLength":1000000,"pricing":{"inputPerM":2,"outputPerM":6},"releasedAt":"2026-09-03","huggingFaceId":null,"profile":{"description":"Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,...","inputModalities":["text","image","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":131072,"knowledgeCutoff":null,"cacheReadPerM":0.25,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3.8-max-20260902"}},{"id":"meta/muse-spark-1.3-contributor","slug":"meta-muse-spark-1-3-contributor","name":"Meta: Muse Spark 1.3 Contributor","provider":"meta","contextLength":1048576,"pricing":{"inputPerM":0.1,"outputPerM":0.2},"releasedAt":"2026-09-02","huggingFaceId":null,"profile":{"description":"Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows. It is designed to track information...","inputModalities":["text","image","video","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":943718,"knowledgeCutoff":null,"cacheReadPerM":0.002,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.0025,"tokenizer":null,"moderated":true,"expiresAt":null,"canonicalSlug":"meta/muse-spark-1.3-contributor-20260902"}},{"id":"meta/muse-spark-1.3","slug":"meta-muse-spark-1-3","name":"Meta: Muse Spark 1.3","provider":"meta","contextLength":1048576,"pricing":{"inputPerM":1.25,"outputPerM":4.25},"releasedAt":"2026-09-02","huggingFaceId":null,"profile":{"description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to keep track of information across extended tasks, work through...","inputModalities":["text","image","video","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":943718,"knowledgeCutoff":null,"cacheReadPerM":0.15,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.0025,"tokenizer":null,"moderated":true,"expiresAt":null,"canonicalSlug":"meta/muse-spark-1.3-20260902"}},{"id":"google/gemini-3.8-flash","slug":"gemini-3-8-flash","name":"Google: Gemini 3.8 Flash","provider":"google","contextLength":1048576,"pricing":{"inputPerM":0.825,"outputPerM":4.125},"releasedAt":"2026-09-02","huggingFaceId":null,"profile":{"description":"Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.","inputModalities":["text","image","video","file","audio"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":65536,"knowledgeCutoff":null,"cacheReadPerM":0.0825,"cacheWritePerM":0.041667,"reasoningPerM":4.125,"webSearchPerRequest":0.014,"tokenizer":"Gemini","moderated":false,"expiresAt":null,"canonicalSlug":"google/gemini-3.8-flash-20260902"}},{"id":"anthropic/claude-fable-5.1","slug":"claude-fable-5-1","name":"Anthropic: Claude Fable 5.1","provider":"anthropic","contextLength":1000000,"pricing":{"inputPerM":10,"outputPerM":50},"releasedAt":"2026-09-01","huggingFaceId":null,"profile":{"description":"Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2026-06","cacheReadPerM":0.25,"cacheWritePerM":12.5,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"Claude","moderated":true,"expiresAt":null,"canonicalSlug":"anthropic/claude-fable-5.1-20260831","knowledgeCutoffSource":{"label":"Anthropic model documentation","url":"https://platform.claude.com/docs/en/models/fable-5-1/overview.md"}}},{"id":"ibm-granite/granite-4.2-8b","slug":"ibm-granite-granite-4-2-8b","name":"IBM: Granite 4.2 8B","provider":"ibm-granite","contextLength":131072,"pricing":{"inputPerM":0.06,"outputPerM":0.25},"releasedAt":"2026-08-31","huggingFaceId":"ibm-granite/granite-4.2-8b","profile":{"description":"Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":117964,"knowledgeCutoff":null,"cacheReadPerM":0.015,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"ibm-granite/granite-4.2-8b-20260831"}},{"id":"tencent/hy4-preview","slug":"tencent-hy4-preview","name":"Tencent: Hy4 preview","provider":"tencent","contextLength":1048576,"pricing":{"inputPerM":0.834,"outputPerM":2.501},"releasedAt":"2026-08-28","huggingFaceId":"tencent/Hy4-preview","profile":{"description":"Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":64000,"knowledgeCutoff":null,"cacheReadPerM":0.042,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"tencent/hy4-preview-20260827"}},{"id":"qwen/qwen3.8-flash","slug":"qwen3-8-flash","name":"Qwen: Qwen3.8 Flash","provider":"qwen","contextLength":1000000,"pricing":{"inputPerM":0.15,"outputPerM":0.47},"releasedAt":"2026-08-26","huggingFaceId":"Qwen/Qwen3.8-Flash-Next","profile":{"description":"Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.","inputModalities":["text","image","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":131072,"knowledgeCutoff":null,"cacheReadPerM":0.016,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3.8-flash-20260826"}},{"id":"z-ai/glm-5.3-flash","slug":"glm-5-3-flash","name":"Z.ai: GLM 5.3 Flash","provider":"z-ai","contextLength":1048576,"pricing":{"inputPerM":0.048,"outputPerM":0.16},"releasedAt":"2026-08-26","huggingFaceId":"zai-org/GLM-5.3-Flash","profile":{"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...","inputModalities":["text","image","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":943718,"knowledgeCutoff":null,"cacheReadPerM":0.006,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"z-ai/glm-5.3-flash-20260826"}},{"id":"meta/muse-spark-1.2-contributor","slug":"meta-muse-spark-1-2-contributor","name":"Meta: Muse Spark 1.2 Contributor","provider":"meta","contextLength":1048576,"pricing":{"inputPerM":0.1,"outputPerM":0.2},"releasedAt":"2026-08-21","huggingFaceId":null,"profile":{"description":"Muse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost. It’s meaningfully cheaper than Muse Spark...","inputModalities":["text","image","video","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":943718,"knowledgeCutoff":null,"cacheReadPerM":0.002,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.0025,"tokenizer":null,"moderated":true,"expiresAt":null,"canonicalSlug":"meta/muse-spark-1.2-contributor-20260805"}},{"id":"deepseek/deepseek-v4-flash-vision-exp","slug":"deepseek-v4-flash-vision-exp","name":"DeepSeek: DeepSeek V4 Flash Vision Exp","provider":"deepseek","contextLength":1048576,"pricing":{"inputPerM":0.2156,"outputPerM":0.6468},"releasedAt":"2026-08-21","huggingFaceId":"deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","profile":{"description":"DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...","inputModalities":["text","image"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":262144,"knowledgeCutoff":null,"cacheReadPerM":0.00686,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"DeepSeek","moderated":false,"expiresAt":null,"canonicalSlug":"deepseek/deepseek-v4-flash-vision-exp-20260821"}},{"id":"tencent/hy-mt2-1.8b","slug":"tencent-hy-mt2-1-8b","name":"Tencent: Hy-MT2-1.8B","provider":"tencent","contextLength":8192,"pricing":{"inputPerM":0.044,"outputPerM":0.177},"releasedAt":"2026-08-20","huggingFaceId":"tencent/Hy-MT2-1.8B","profile":{"description":"Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided...","inputModalities":["text"],"outputModalities":["text"],"features":[],"maxOutput":4096,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"tencent/hy-mt2-1.8b-20260521"}},{"id":"tencent/hy-mt2-30b-a3b","slug":"tencent-hy-mt2-30b-a3b","name":"Tencent: Hy-MT2-30B-A3B","provider":"tencent","contextLength":8192,"pricing":{"inputPerM":0.074,"outputPerM":0.295},"releasedAt":"2026-08-20","huggingFaceId":"tencent/Hy-MT2-30B-A3B","profile":{"description":"Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and...","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs"],"maxOutput":4096,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"tencent/hy-mt2-30b-a3b-20260521"}},{"id":"tencent/hy-mt2-7b","slug":"tencent-hy-mt2-7b","name":"Tencent: Hy-MT2-7B","provider":"tencent","contextLength":8192,"pricing":{"inputPerM":0.074,"outputPerM":0.295},"releasedAt":"2026-08-19","huggingFaceId":"tencent/Hy-MT2-7B","profile":{"description":"Hy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation.","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs"],"maxOutput":4096,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"tencent/hy-mt2-7b-20260521"}},{"id":"z-ai/glm-5.3","slug":"glm-5-3","name":"Z.ai: GLM 5.3","provider":"z-ai","contextLength":1048576,"pricing":{"inputPerM":0.079,"outputPerM":1.4},"releasedAt":"2026-08-18","huggingFaceId":"zai-org/GLM-5.3","profile":{"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":943718,"knowledgeCutoff":null,"cacheReadPerM":0.078,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"z-ai/glm-5.3-20260816"}},{"id":"qwen/qwen3.8-27b","slug":"qwen3-8-27b","name":"Qwen: Qwen3.8 27B","provider":"qwen","contextLength":1000000,"pricing":{"inputPerM":0.24,"outputPerM":2.2},"releasedAt":"2026-08-14","huggingFaceId":"Qwen/Qwen3.8-27B","profile":{"description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...","inputModalities":["text","image","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":235929,"knowledgeCutoff":null,"cacheReadPerM":0.05,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3.8-27b-20260814"}},{"id":"google/gemini-3.7-flash","slug":"gemini-3-7-flash","name":"Google: Gemini 3.7 Flash","provider":"google","contextLength":1048576,"pricing":{"inputPerM":0.75,"outputPerM":3.75},"releasedAt":"2026-08-13","huggingFaceId":null,"profile":{"description":"Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...","inputModalities":["text","image","video","file","audio"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":65536,"knowledgeCutoff":null,"cacheReadPerM":0.075,"cacheWritePerM":0.041667,"reasoningPerM":3.75,"webSearchPerRequest":0.014,"tokenizer":"Gemini","moderated":false,"expiresAt":null,"canonicalSlug":"google/gemini-3.7-flash-20260813"}},{"id":"bytedance-seed/seed-2-1-turbo","slug":"bytedance-seed-seed-2-1-turbo","name":"ByteDance Seed: Seed 2.1 Turbo","provider":"bytedance-seed","contextLength":262144,"pricing":{"inputPerM":0.5,"outputPerM":2.5},"releasedAt":"2026-08-12","huggingFaceId":null,"profile":{"description":"Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows. It is suited for end-to-end software delivery, multi-step task execution, and understanding visual and...","inputModalities":["text","image","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":235929,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"bytedance-seed/seed-2-1-turbo-20260810"}},{"id":"qwen/qwen3.8-2.4t-a95b","slug":"qwen3-8-2-4t-a95b","name":"Qwen: Qwen3.8 2.4T A95B","provider":"qwen","contextLength":1048576,"pricing":{"inputPerM":2,"outputPerM":6},"releasedAt":"2026-08-12","huggingFaceId":"Qwen/Qwen3.8-2.4T-A95B","profile":{"description":"Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":131072,"knowledgeCutoff":null,"cacheReadPerM":0.25,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3.8-2.4t-a95b-20260812"}},{"id":"bytedance-seed/seed-2.0-code","slug":"bytedance-seed-seed-2-0-code","name":"ByteDance Seed: Seed-2.0-Code","provider":"bytedance-seed","contextLength":262144,"pricing":{"inputPerM":0.5,"outputPerM":3},"releasedAt":"2026-08-12","huggingFaceId":null,"profile":{"description":"Seed 2.0 Code is a model from ByteDance Seed optimized for agentic coding. It is suited for frontend development, multilingual programming tasks, and coding-agent workflows in tools such as Claude...","inputModalities":["text","image","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":131072,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":"2026-11-11","canonicalSlug":"bytedance-seed/seed-2.0-code-20260730"}},{"id":"deepseek/deepseek-v4-pro-0813","slug":"deepseek-v4-pro-0813","name":"DeepSeek: DeepSeek V4 Pro 0813","provider":"deepseek","contextLength":1048576,"pricing":{"inputPerM":0.66,"outputPerM":1.98},"releasedAt":"2026-08-12","huggingFaceId":"deepseek-ai/DeepSeek-V4-Pro-0813","profile":{"description":"DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":384000,"knowledgeCutoff":null,"cacheReadPerM":0.022,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"DeepSeek","moderated":false,"expiresAt":null,"canonicalSlug":"deepseek/deepseek-v4-pro-20260813"}},{"id":"x-ai/grok-4.6","slug":"grok-4-6","name":"SpaceXAI: Grok 4.6","provider":"x-ai","contextLength":500000,"pricing":{"inputPerM":2,"outputPerM":6},"releasedAt":"2026-08-12","huggingFaceId":null,"profile":{"description":"Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by [Grok 4.7](/x-ai/grok-4.7).","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":450000,"knowledgeCutoff":null,"cacheReadPerM":0.5,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.005,"tokenizer":"Grok","moderated":false,"expiresAt":null,"canonicalSlug":"x-ai/grok-4.6-20260810"}},{"id":"nvidia/nemotron-3.5-lightning","slug":"nvidia-nemotron-3-5-lightning","name":"NVIDIA: Nemotron 3.5 Lightning","provider":"nvidia","contextLength":262144,"pricing":{"inputPerM":0.07,"outputPerM":0.2},"releasedAt":"2026-08-11","huggingFaceId":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16","profile":{"description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":235929,"knowledgeCutoff":null,"cacheReadPerM":0.04,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"nvidia/nemotron-3.5-lightning-20260807"}},{"id":"sakana/sakana-namazu","slug":"sakana-sakana-namazu","name":"Sakana: Sakana Namazu","provider":"sakana","contextLength":262144,"pricing":{"inputPerM":0.95,"outputPerM":4},"releasedAt":"2026-08-11","huggingFaceId":null,"profile":{"description":"Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts. It is suited for Japanese instruction following,...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["reasoning","structured-outputs","tools","web-search"],"maxOutput":65536,"knowledgeCutoff":null,"cacheReadPerM":0.15,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.007,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"sakana/namazu-20260811"}},{"id":"upstage/solar-pro4","slug":"upstage-solar-pro4","name":"Upstage: Solar Pro 4","provider":"upstage","contextLength":524288,"pricing":{"inputPerM":0.15,"outputPerM":0.6},"releasedAt":"2026-08-10","huggingFaceId":null,"profile":{"description":"Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":131072,"knowledgeCutoff":null,"cacheReadPerM":0.03,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"upstage/solar-pro4-20260810"}},{"id":"meta/muse-glimmer-30b","slug":"meta-muse-glimmer-30b","name":"Meta: Muse Glimmer 30B","provider":"meta","contextLength":131072,"pricing":{"inputPerM":0.3,"outputPerM":1.2},"releasedAt":"2026-08-09","huggingFaceId":"meta-models/Muse-Glimmer-30B","profile":{"description":"Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...","inputModalities":["text","image"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":16384,"knowledgeCutoff":null,"cacheReadPerM":0.04,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"meta/muse-glimmer-30b-20260810"}},{"id":"meta/muse-spark-1.2","slug":"meta-muse-spark-1-2","name":"Meta: Muse Spark 1.2","provider":"meta","contextLength":1048576,"pricing":{"inputPerM":1.25,"outputPerM":4.25},"releasedAt":"2026-08-05","huggingFaceId":null,"profile":{"description":"Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, and PDF documents, returns text, and offers a 1M-token context window....","inputModalities":["text","image","video","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":943718,"knowledgeCutoff":null,"cacheReadPerM":0.15,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.0025,"tokenizer":null,"moderated":true,"expiresAt":null,"canonicalSlug":"meta/muse-spark-1.2-20260805"}},{"id":"deepseek/deepseek-v4-flash-0731","slug":"deepseek-v4-flash-0731","name":"DeepSeek: DeepSeek V4 Flash 0731","provider":"deepseek","contextLength":1048576,"pricing":{"inputPerM":0.44,"outputPerM":1.32},"releasedAt":"2026-07-31","huggingFaceId":"deepseek-ai/DeepSeek-V4-Flash-0731","profile":{"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":131072,"knowledgeCutoff":null,"cacheReadPerM":0.014,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"DeepSeek","moderated":false,"expiresAt":null,"canonicalSlug":"deepseek/deepseek-v4-flash-20260731"}},{"id":"thinkingmachines/inkling-small","slug":"thinkingmachines-inkling-small","name":"Thinking Machines: Inkling Small","provider":"thinkingmachines","contextLength":524288,"pricing":{"inputPerM":0.45,"outputPerM":1.2},"releasedAt":"2026-07-30","huggingFaceId":"thinkingmachines/Inkling-Small","profile":{"description":"Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...","inputModalities":["text","image","audio"],"outputModalities":["text"],"features":["reasoning","tools"],"maxOutput":262144,"knowledgeCutoff":null,"cacheReadPerM":0.1,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"thinkingmachines/inkling-small-20260730"}},{"id":"qwen/qwen3.7-flash","slug":"qwen3-7-flash","name":"Qwen: Qwen3.7 Flash","provider":"qwen","contextLength":1000000,"pricing":{"inputPerM":0.03,"outputPerM":0.13},"releasedAt":"2026-07-27","huggingFaceId":null,"profile":{"description":"Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...","inputModalities":["text","image","video"],"outputModalities":["text"],"features":["reasoning","json-mode","tools"],"maxOutput":65536,"knowledgeCutoff":null,"cacheReadPerM":0.006,"cacheWritePerM":0.038,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3.7-flash-20260727"}},{"id":"anthropic/claude-opus-5","slug":"claude-opus-5","name":"Anthropic: Claude Opus 5","provider":"anthropic","contextLength":1000000,"pricing":{"inputPerM":5,"outputPerM":25},"releasedAt":"2026-07-24","huggingFaceId":null,"profile":{"description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2026-05","cacheReadPerM":0.5,"cacheWritePerM":6.25,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"Claude","moderated":true,"expiresAt":null,"canonicalSlug":"anthropic/claude-opus-5-20260723","knowledgeCutoffSource":{"label":"Anthropic model documentation","url":"https://platform.claude.com/docs/en/models/opus-5/overview.md"}}},{"id":"inclusionai/ling-3.0-flash","slug":"inclusionai-ling-3-0-flash","name":"inclusionAI: Ling 3.0 Flash","provider":"inclusionai","contextLength":262144,"pricing":{"inputPerM":0.021,"outputPerM":0.063},"releasedAt":"2026-07-23","huggingFaceId":"inclusionAI/Ling-3.0-flash","profile":{"description":"*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","tools"],"maxOutput":32768,"knowledgeCutoff":null,"cacheReadPerM":0.0042,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"inclusionai/ling-3.0-flash-20260723"}},{"id":"poolside/laguna-s-2.1","slug":"poolside-laguna-s-2-1","name":"Poolside: Laguna S 2.1","provider":"poolside","contextLength":1048576,"pricing":{"inputPerM":0.09,"outputPerM":0.18},"releasedAt":"2026-07-21","huggingFaceId":"poolside/Laguna-S-2.1","profile":{"description":"Laguna S 2.1 is the latest coding agent model from [Poolside](). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","tools"],"maxOutput":131072,"knowledgeCutoff":null,"cacheReadPerM":0.009,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":"2026-10-31","canonicalSlug":"poolside/laguna-s-2.1-20260720"}},{"id":"google/gemini-3.6-flash","slug":"gemini-3-6-flash","name":"Google: Gemini 3.6 Flash","provider":"google","contextLength":1048576,"pricing":{"inputPerM":0.75,"outputPerM":3.75},"releasedAt":"2026-07-21","huggingFaceId":null,"profile":{"description":"Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...","inputModalities":["text","image","video","file","audio"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":65536,"knowledgeCutoff":null,"cacheReadPerM":0.075,"cacheWritePerM":0.041667,"reasoningPerM":3.75,"webSearchPerRequest":0.014,"tokenizer":"Gemini","moderated":false,"expiresAt":null,"canonicalSlug":"google/gemini-3.6-flash-20260721"}},{"id":"google/gemini-3.5-flash-lite","slug":"gemini-3-5-flash-lite","name":"Google: Gemini 3.5 Flash Lite","provider":"google","contextLength":1048576,"pricing":{"inputPerM":0.3,"outputPerM":2.5},"releasedAt":"2026-07-21","huggingFaceId":null,"profile":{"description":"Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.","inputModalities":["text","image","video","file","audio"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":65536,"knowledgeCutoff":null,"cacheReadPerM":0.03,"cacheWritePerM":0.083333,"reasoningPerM":2.5,"webSearchPerRequest":0.014,"tokenizer":"Gemini","moderated":false,"expiresAt":null,"canonicalSlug":"google/gemini-3.5-flash-lite-20260721"}},{"id":"meituan/longcat-2.0","slug":"meituan-longcat-2-0","name":"Meituan: LongCat 2.0","provider":"meituan","contextLength":1048756,"pricing":{"inputPerM":0.3,"outputPerM":1.2},"releasedAt":"2026-07-20","huggingFaceId":"meituan-longcat/LongCat-2.0","profile":{"description":"LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","tools"],"maxOutput":262144,"knowledgeCutoff":null,"cacheReadPerM":0.006,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"meituan/longcat-2.0-20260720"}},{"id":"thinkingmachines/inkling","slug":"thinkingmachines-inkling","name":"Thinking Machines: Inkling","provider":"thinkingmachines","contextLength":524288,"pricing":{"inputPerM":1,"outputPerM":4.05},"releasedAt":"2026-07-17","huggingFaceId":"thinkingmachines/Inkling","profile":{"description":"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...","inputModalities":["text","image","audio"],"outputModalities":["text"],"features":["reasoning","tools"],"maxOutput":471859,"knowledgeCutoff":null,"cacheReadPerM":0.17,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"thinkingmachines/inkling-20260715"}},{"id":"openrouter/auto-beta","slug":"openrouter-auto-beta","name":"Auto Router (Beta)","provider":"openrouter","contextLength":2000000,"pricing":null,"releasedAt":"2026-07-17","huggingFaceId":null,"profile":{"description":"The experimental version of our Auto Router where we test new improvements. Use it to get the latest and greatest version of our general purpose auto router, but expect beta...","inputModalities":["text","image","audio","file","video"],"outputModalities":["text","image"],"features":["reasoning","json-mode","structured-outputs","tools","web-search"],"maxOutput":null,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Router","moderated":false,"expiresAt":null,"canonicalSlug":"openrouter/auto-beta"}},{"id":"moonshotai/kimi-k3","slug":"kimi-k3","name":"MoonshotAI: Kimi K3","provider":"moonshotai","contextLength":1048576,"pricing":{"inputPerM":0.239,"outputPerM":11.936},"releasedAt":"2026-07-16","huggingFaceId":"moonshotai/Kimi-K3","profile":{"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...","inputModalities":["text","image","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":943718,"knowledgeCutoff":null,"cacheReadPerM":0.21,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"moonshotai/kimi-k3-20260715"}},{"id":"meta/muse-spark-1.1","slug":"meta-muse-spark-1-1","name":"Meta: Muse Spark 1.1","provider":"meta","contextLength":1048576,"pricing":{"inputPerM":1.25,"outputPerM":4.25},"releasedAt":"2026-07-16","huggingFaceId":null,"profile":{"description":"Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, and PDF documents and returns text, with a 1M-token context window....","inputModalities":["text","image","video","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":943718,"knowledgeCutoff":null,"cacheReadPerM":0.15,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.0025,"tokenizer":null,"moderated":true,"expiresAt":null,"canonicalSlug":"meta/muse-spark-1.1-20260709"}},{"id":"openai/gpt-5.6-luna-pro","slug":"gpt-5-6-luna-pro","name":"OpenAI: GPT-5.6 Luna Pro","provider":"openai","contextLength":1050000,"pricing":{"inputPerM":0.2,"outputPerM":1.2},"releasedAt":"2026-07-09","huggingFaceId":null,"profile":{"description":"GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","inputModalities":["file","image","text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2026-02-16","cacheReadPerM":0.02,"cacheWritePerM":0.25,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-5.6-luna-pro-20260709"}},{"id":"openai/gpt-5.6-luna","slug":"gpt-5-6-luna","name":"OpenAI: GPT-5.6 Luna","provider":"openai","contextLength":1050000,"pricing":{"inputPerM":0.2,"outputPerM":1.2},"releasedAt":"2026-07-09","huggingFaceId":null,"profile":{"description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...","inputModalities":["file","image","text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2026-02-16","cacheReadPerM":0.02,"cacheWritePerM":0.25,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-5.6-luna-20260709"}},{"id":"openai/gpt-5.6-terra-pro","slug":"gpt-5-6-terra-pro","name":"OpenAI: GPT-5.6 Terra Pro","provider":"openai","contextLength":1050000,"pricing":{"inputPerM":2,"outputPerM":12},"releasedAt":"2026-07-09","huggingFaceId":null,"profile":{"description":"GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","inputModalities":["file","image","text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2026-02-16","cacheReadPerM":0.2,"cacheWritePerM":2.5,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-5.6-terra-pro-20260709"}},{"id":"openai/gpt-5.6-terra","slug":"gpt-5-6-terra","name":"OpenAI: GPT-5.6 Terra","provider":"openai","contextLength":1050000,"pricing":{"inputPerM":2,"outputPerM":12},"releasedAt":"2026-07-09","huggingFaceId":null,"profile":{"description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...","inputModalities":["file","image","text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2026-02-16","cacheReadPerM":0.2,"cacheWritePerM":2.5,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-5.6-terra-20260709"}},{"id":"openai/gpt-5.6-sol-pro","slug":"gpt-5-6-sol-pro","name":"OpenAI: GPT-5.6 Sol Pro","provider":"openai","contextLength":1050000,"pricing":{"inputPerM":4,"outputPerM":20},"releasedAt":"2026-07-09","huggingFaceId":null,"profile":{"description":"GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","inputModalities":["file","image","text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2026-02-16","cacheReadPerM":0.4,"cacheWritePerM":5,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-5.6-sol-pro-20260709"}},{"id":"openai/gpt-5.6-sol","slug":"gpt-5-6-sol","name":"OpenAI: GPT-5.6 Sol","provider":"openai","contextLength":1050000,"pricing":{"inputPerM":4,"outputPerM":20},"releasedAt":"2026-07-09","huggingFaceId":null,"profile":{"description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...","inputModalities":["file","image","text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2026-02-16","cacheReadPerM":0.4,"cacheWritePerM":5,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-5.6-sol-20260709"}},{"id":"x-ai/grok-4.5","slug":"grok-4-5","name":"SpaceXAI: Grok 4.5","provider":"x-ai","contextLength":500000,"pricing":{"inputPerM":2,"outputPerM":6},"releasedAt":"2026-07-08","huggingFaceId":null,"profile":{"description":"Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":450000,"knowledgeCutoff":null,"cacheReadPerM":0.3,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.005,"tokenizer":"Grok","moderated":false,"expiresAt":null,"canonicalSlug":"x-ai/grok-4.5-20260708"}},{"id":"aion-labs/aion-3.0-mini","slug":"aion-labs-aion-3-0-mini","name":"AionLabs: Aion-3.0-Mini","provider":"aion-labs","contextLength":131072,"pricing":{"inputPerM":0.7,"outputPerM":1.4},"releasedAt":"2026-07-07","huggingFaceId":null,"profile":{"description":"Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","tools"],"maxOutput":32768,"knowledgeCutoff":null,"cacheReadPerM":0.18,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"aion-labs/aion-3.0-mini-20260707"}},{"id":"aion-labs/aion-3.0","slug":"aion-labs-aion-3-0","name":"AionLabs: Aion-3.0","provider":"aion-labs","contextLength":131072,"pricing":{"inputPerM":3,"outputPerM":6},"releasedAt":"2026-07-07","huggingFaceId":null,"profile":{"description":"Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","tools"],"maxOutput":32768,"knowledgeCutoff":null,"cacheReadPerM":0.75,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"aion-labs/aion-3.0-20260707"}},{"id":"tencent/hy3","slug":"tencent-hy3","name":"Tencent: Hy3","provider":"tencent","contextLength":262144,"pricing":{"inputPerM":0.132,"outputPerM":0.528},"releasedAt":"2026-07-06","huggingFaceId":"tencent/Hy3","profile":{"description":"Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":null,"cacheReadPerM":0.033,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"tencent/hy3-20260706"}},{"id":"poolside/laguna-xs-2.1","slug":"poolside-laguna-xs-2-1","name":"Poolside: Laguna XS 2.1","provider":"poolside","contextLength":262144,"pricing":{"inputPerM":0.06,"outputPerM":0.12},"releasedAt":"2026-07-02","huggingFaceId":"poolside/Laguna-XS-2.1","profile":{"description":"Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","tools"],"maxOutput":32768,"knowledgeCutoff":null,"cacheReadPerM":0.03,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":"2026-10-31","canonicalSlug":"poolside/laguna-xs-2.1-20260625"}},{"id":"anthropic/claude-sonnet-5","slug":"claude-sonnet-5","name":"Anthropic: Claude Sonnet 5","provider":"anthropic","contextLength":1000000,"pricing":{"inputPerM":2,"outputPerM":10},"releasedAt":"2026-06-30","huggingFaceId":null,"profile":{"description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2026-01","cacheReadPerM":0.2,"cacheWritePerM":2.5,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"Claude","moderated":true,"expiresAt":null,"canonicalSlug":"anthropic/claude-sonnet-5-20260630","knowledgeCutoffSource":{"label":"Anthropic model documentation","url":"https://platform.claude.com/docs/en/models/sonnet-5/overview.md"}}},{"id":"google/gemini-3.1-flash-lite-image","slug":"gemini-3-1-flash-lite-image","name":"Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)","provider":"google","contextLength":65536,"pricing":{"inputPerM":0.25,"outputPerM":1.5},"releasedAt":"2026-06-30","huggingFaceId":null,"profile":{"description":"Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation...","inputModalities":["image","text"],"outputModalities":["image","text"],"features":["reasoning","json-mode"],"maxOutput":58982,"knowledgeCutoff":"2025-01-01","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.014,"tokenizer":"Gemini","moderated":false,"expiresAt":null,"canonicalSlug":"google/gemini-3.1-flash-lite-image-20260630"}},{"id":"sakana/fugu-ultra","slug":"sakana-fugu-ultra","name":"Sakana: Fugu Ultra","provider":"sakana","contextLength":1000000,"pricing":{"inputPerM":5,"outputPerM":30},"releasedAt":"2026-06-24","huggingFaceId":null,"profile":{"description":"Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...","inputModalities":["text","image"],"outputModalities":["text"],"features":["reasoning","structured-outputs","tools","web-search"],"maxOutput":128000,"knowledgeCutoff":null,"cacheReadPerM":0.5,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"sakana/fugu-ultra-20260615"}},{"id":"google/gemini-3.1-flash-image","slug":"gemini-3-1-flash-image","name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image)","provider":"google","contextLength":131072,"pricing":{"inputPerM":0.5,"outputPerM":3},"releasedAt":"2026-06-18","huggingFaceId":null,"profile":{"description":"Gemini 3.1 Flash Image, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...","inputModalities":["image","text"],"outputModalities":["image","text"],"features":["reasoning","json-mode","structured-outputs"],"maxOutput":32768,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.014,"tokenizer":"Gemini","moderated":false,"expiresAt":null,"canonicalSlug":"google/gemini-3.1-flash-image-20260528"}},{"id":"google/gemini-3-pro-image","slug":"gemini-3-pro-image","name":"Google: Nano Banana Pro (Gemini 3 Pro Image)","provider":"google","contextLength":131072,"pricing":{"inputPerM":2,"outputPerM":12},"releasedAt":"2026-06-18","huggingFaceId":null,"profile":{"description":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...","inputModalities":["image","text"],"outputModalities":["image","text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":32768,"knowledgeCutoff":null,"cacheReadPerM":0.2,"cacheWritePerM":0.375,"reasoningPerM":12,"webSearchPerRequest":0.014,"tokenizer":"Gemini","moderated":false,"expiresAt":null,"canonicalSlug":"google/gemini-3-pro-image-20260528"}},{"id":"z-ai/glm-5.2","slug":"glm-5-2","name":"Z.ai: GLM 5.2","provider":"z-ai","contextLength":1048576,"pricing":{"inputPerM":0.62,"outputPerM":2.42},"releasedAt":"2026-06-16","huggingFaceId":"zai-org/GLM-5.2","profile":{"description":"GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":943718,"knowledgeCutoff":null,"cacheReadPerM":0.14,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"z-ai/glm-5.2-20260616"}},{"id":"openrouter/fusion","slug":"openrouter-fusion","name":"OpenRouter: Fusion","provider":"openrouter","contextLength":1000000,"pricing":null,"releasedAt":"2026-06-13","huggingFaceId":null,"profile":{"description":"Fusion turns your prompt into a small multi-model deliberation. A panel of expert models (see below) analyzes your prompt in parallel with web search and web fetch enabled, then a...","inputModalities":["text"],"outputModalities":["text"],"features":[],"maxOutput":null,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Router","moderated":false,"expiresAt":null,"canonicalSlug":"openrouter/fusion"}},{"id":"moonshotai/kimi-k2.7-code","slug":"kimi-k2-7-code","name":"MoonshotAI: Kimi K2.7 Code","provider":"moonshotai","contextLength":262144,"pricing":{"inputPerM":0.6712,"outputPerM":3.35},"releasedAt":"2026-06-12","huggingFaceId":"moonshotai/Kimi-K2.7-Code","profile":{"description":"MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...","inputModalities":["text","image"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":235929,"knowledgeCutoff":null,"cacheReadPerM":0.18,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"moonshotai/kimi-k2.7-code-20260612"}},{"id":"anthropic/claude-fable-5","slug":"claude-fable-5","name":"Anthropic: Claude Fable 5","provider":"anthropic","contextLength":1000000,"pricing":{"inputPerM":10,"outputPerM":50},"releasedAt":"2026-06-09","huggingFaceId":null,"profile":{"description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2026-01","cacheReadPerM":1,"cacheWritePerM":12.5,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"Claude","moderated":true,"expiresAt":null,"canonicalSlug":"anthropic/claude-5-fable-20260609","knowledgeCutoffSource":{"label":"Anthropic model documentation","url":"https://platform.claude.com/docs/en/models/fable-5/overview.md"}}},{"id":"nvidia/nemotron-3.5-content-safety","slug":"nvidia-nemotron-3-5-content-safety","name":"NVIDIA: Nemotron 3.5 Content Safety","provider":"nvidia","contextLength":131072,"pricing":{"inputPerM":0.2,"outputPerM":0.2},"releasedAt":"2026-06-04","huggingFaceId":"nvidia/Nemotron-3.5-Content-Safety","profile":{"description":"NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...","inputModalities":["text","image"],"outputModalities":["text"],"features":["reasoning"],"maxOutput":117964,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"nvidia/nemotron-3.5-content-safety-20260604"}},{"id":"nvidia/nemotron-3-ultra-550b-a55b","slug":"nvidia-nemotron-3-ultra-550b-a55b","name":"NVIDIA: Nemotron 3 Ultra","provider":"nvidia","contextLength":262144,"pricing":{"inputPerM":0.6,"outputPerM":2.4},"releasedAt":"2026-06-04","huggingFaceId":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","profile":{"description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":182520,"knowledgeCutoff":null,"cacheReadPerM":0.12,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"nvidia/nemotron-3-ultra-550b-a55b-20260604"}},{"id":"qwen/qwen3.7-plus","slug":"qwen3-7-plus","name":"Qwen: Qwen3.7 Plus","provider":"qwen","contextLength":1000000,"pricing":{"inputPerM":0.32,"outputPerM":1.28},"releasedAt":"2026-06-03","huggingFaceId":null,"profile":{"description":"Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...","inputModalities":["text","image"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":131072,"knowledgeCutoff":null,"cacheReadPerM":0.064,"cacheWritePerM":0.4,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3.7-plus-20260602"}},{"id":"minimax/minimax-m3","slug":"minimax-minimax-m3","name":"MiniMax: MiniMax M3","provider":"minimax","contextLength":1048576,"pricing":{"inputPerM":0.3,"outputPerM":1.2},"releasedAt":"2026-05-31","huggingFaceId":"MiniMaxAI/Minimax-M3","profile":{"description":"MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...","inputModalities":["text","image","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":512000,"knowledgeCutoff":null,"cacheReadPerM":0.06,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"minimax/minimax-m3-20260531"}},{"id":"stepfun/step-3.7-flash","slug":"stepfun-step-3-7-flash","name":"StepFun: Step 3.7 Flash","provider":"stepfun","contextLength":262144,"pricing":{"inputPerM":0.2,"outputPerM":1.15},"releasedAt":"2026-05-28","huggingFaceId":"stepfun-ai/Step-3.7-Flash","profile":{"description":"Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...","inputModalities":["text","image","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":230400,"knowledgeCutoff":null,"cacheReadPerM":0.04,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"stepfun/step-3.7-flash-20260528"}},{"id":"anthropic/claude-opus-4.8","slug":"claude-opus-4-8","name":"Anthropic: Claude Opus 4.8","provider":"anthropic","contextLength":1000000,"pricing":{"inputPerM":5,"outputPerM":25},"releasedAt":"2026-05-27","huggingFaceId":null,"profile":{"description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2026-01","cacheReadPerM":0.5,"cacheWritePerM":6.25,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"Claude","moderated":true,"expiresAt":null,"canonicalSlug":"anthropic/claude-4.8-opus-20260528","knowledgeCutoffSource":{"label":"Anthropic model documentation","url":"https://platform.claude.com/docs/en/models/opus-4-8/overview.md"}}},{"id":"qwen/qwen3.7-max","slug":"qwen3-7-max","name":"Qwen: Qwen3.7 Max","provider":"qwen","contextLength":1000000,"pricing":{"inputPerM":1.475,"outputPerM":4.425},"releasedAt":"2026-05-21","huggingFaceId":null,"profile":{"description":"Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":131072,"knowledgeCutoff":null,"cacheReadPerM":0.295,"cacheWritePerM":1.84375,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3.7-max-20260520"}},{"id":"x-ai/grok-build-0.1","slug":"grok-build-0-1","name":"SpaceXAI: Grok Build 0.1","provider":"x-ai","contextLength":256000,"pricing":{"inputPerM":1,"outputPerM":2},"releasedAt":"2026-05-20","huggingFaceId":null,"profile":{"description":"Grok Build 0.1 is SpaceXAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":230400,"knowledgeCutoff":null,"cacheReadPerM":0.2,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.005,"tokenizer":"Grok","moderated":false,"expiresAt":null,"canonicalSlug":"x-ai/grok-build-0.1-20260520"}},{"id":"google/gemini-3.5-flash","slug":"gemini-3-5-flash","name":"Google: Gemini 3.5 Flash","provider":"google","contextLength":1048576,"pricing":{"inputPerM":1.5,"outputPerM":9},"releasedAt":"2026-05-19","huggingFaceId":null,"profile":{"description":"Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...","inputModalities":["text","image","video","file","audio"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":65536,"knowledgeCutoff":"2025-01-01","cacheReadPerM":0.15,"cacheWritePerM":0.083333,"reasoningPerM":9,"webSearchPerRequest":0.014,"tokenizer":"Gemini","moderated":false,"expiresAt":null,"canonicalSlug":"google/gemini-3.5-flash-20260519"}},{"id":"perceptron/perceptron-mk1","slug":"perceptron-perceptron-mk1","name":"Perceptron: Perceptron Mk1","provider":"perceptron","contextLength":32768,"pricing":{"inputPerM":0.15,"outputPerM":1.5},"releasedAt":"2026-05-12","huggingFaceId":null,"profile":{"description":"Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired with natural language queries, and produces detailed visual understanding...","inputModalities":["text","image","video"],"outputModalities":["text"],"features":["reasoning","structured-outputs"],"maxOutput":8192,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"perceptron/perceptron-mk1-20260512"}},{"id":"google/gemini-3.1-flash-lite","slug":"gemini-3-1-flash-lite","name":"Google: Gemini 3.1 Flash Lite","provider":"google","contextLength":1048576,"pricing":{"inputPerM":0.25,"outputPerM":1.5},"releasedAt":"2026-05-07","huggingFaceId":null,"profile":{"description":"Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...","inputModalities":["text","image","video","file","audio"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":65536,"knowledgeCutoff":null,"cacheReadPerM":0.025,"cacheWritePerM":0.083333,"reasoningPerM":1.5,"webSearchPerRequest":0.014,"tokenizer":"Gemini","moderated":false,"expiresAt":null,"canonicalSlug":"google/gemini-3.1-flash-lite-20260507"}},{"id":"openai/gpt-chat-latest","slug":"gpt-chat-latest","name":"OpenAI: GPT Chat Latest","provider":"openai","contextLength":400000,"pricing":{"inputPerM":5,"outputPerM":30},"releasedAt":"2026-05-05","huggingFaceId":null,"profile":{"description":"GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updates...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":null,"cacheReadPerM":0.5,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-chat-latest-20260505"}},{"id":"x-ai/grok-4.3","slug":"grok-4-3","name":"SpaceXAI: Grok 4.3","provider":"x-ai","contextLength":1000000,"pricing":{"inputPerM":1.25,"outputPerM":2.5},"releasedAt":"2026-04-30","huggingFaceId":null,"profile":{"description":"Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":900000,"knowledgeCutoff":null,"cacheReadPerM":0.2,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.005,"tokenizer":"Grok","moderated":false,"expiresAt":null,"canonicalSlug":"x-ai/grok-4.3-20260430"}},{"id":"mistralai/mistral-medium-3-5","slug":"mistral-medium-3-5","name":"Mistral: Mistral Medium 3.5","provider":"mistralai","contextLength":262144,"pricing":{"inputPerM":1.5,"outputPerM":7.5},"releasedAt":"2026-04-30","huggingFaceId":null,"profile":{"description":"Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":209715,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Mistral","moderated":false,"expiresAt":null,"canonicalSlug":"mistralai/mistral-medium-3.5-20260430"}},{"id":"qwen/qwen3.5-plus-20260420","slug":"qwen3-5-plus-20260420","name":"Qwen: Qwen3.5 Plus 2026-04-20","provider":"qwen","contextLength":1000000,"pricing":{"inputPerM":0.3,"outputPerM":1.8},"releasedAt":"2026-04-27","huggingFaceId":null,"profile":{"description":"Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This...","inputModalities":["text","image","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":65536,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":0.375,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen3","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3.5-plus-20260420"}},{"id":"qwen/qwen3.6-flash","slug":"qwen3-6-flash","name":"Qwen: Qwen3.6 Flash","provider":"qwen","contextLength":1000000,"pricing":{"inputPerM":0.1875,"outputPerM":1.125},"releasedAt":"2026-04-27","huggingFaceId":null,"profile":{"description":"Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in...","inputModalities":["text","image","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":65536,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":0.234375,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen3","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3.6-flash"}},{"id":"qwen/qwen3.6-35b-a3b","slug":"qwen3-6-35b-a3b","name":"Qwen: Qwen3.6 35B A3B","provider":"qwen","contextLength":262144,"pricing":{"inputPerM":0.1,"outputPerM":0.95},"releasedAt":"2026-04-27","huggingFaceId":"Qwen/Qwen3.6-35B-A3B","profile":{"description":"Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...","inputModalities":["text","image","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":235929,"knowledgeCutoff":null,"cacheReadPerM":0.05,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3.6-35b-a3b-20260415"}},{"id":"qwen/qwen3.6-27b","slug":"qwen3-6-27b","name":"Qwen: Qwen3.6 27B","provider":"qwen","contextLength":262144,"pricing":{"inputPerM":0.25,"outputPerM":2},"releasedAt":"2026-04-27","huggingFaceId":"Qwen/Qwen3.6-27B","profile":{"description":"Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities, accepting text, image, and video inputs...","inputModalities":["text","image","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":65536,"knowledgeCutoff":null,"cacheReadPerM":0.025,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen3","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3.6-27b-20260422"}},{"id":"openai/gpt-5.5-pro","slug":"gpt-5-5-pro","name":"OpenAI: GPT-5.5 Pro","provider":"openai","contextLength":1050000,"pricing":{"inputPerM":30,"outputPerM":180},"releasedAt":"2026-04-24","huggingFaceId":null,"profile":{"description":"GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...","inputModalities":["file","image","text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2025-12-01","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-5.5-pro-20260423"}},{"id":"openai/gpt-5.5","slug":"gpt-5-5","name":"OpenAI: GPT-5.5","provider":"openai","contextLength":1050000,"pricing":{"inputPerM":5,"outputPerM":30},"releasedAt":"2026-04-24","huggingFaceId":null,"profile":{"description":"GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...","inputModalities":["file","image","text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2025-12-01","cacheReadPerM":0.5,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-5.5-20260423"}},{"id":"deepseek/deepseek-v4-pro","slug":"deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro 0423","provider":"deepseek","contextLength":1048576,"pricing":{"inputPerM":0.95526,"outputPerM":1.91052},"releasedAt":"2026-04-24","huggingFaceId":"deepseek-ai/DeepSeek-V4-Pro","profile":{"description":"DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":384000,"knowledgeCutoff":null,"cacheReadPerM":0.079605,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"DeepSeek","moderated":false,"expiresAt":null,"canonicalSlug":"deepseek/deepseek-v4-pro-20260423"}},{"id":"deepseek/deepseek-v4-flash","slug":"deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash 0423","provider":"deepseek","contextLength":1048576,"pricing":{"inputPerM":0.091,"outputPerM":0.182},"releasedAt":"2026-04-24","huggingFaceId":"deepseek-ai/DeepSeek-V4-Flash","profile":{"description":"DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":943717,"knowledgeCutoff":null,"cacheReadPerM":0.0182,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"DeepSeek","moderated":false,"expiresAt":null,"canonicalSlug":"deepseek/deepseek-v4-flash-20260423"}},{"id":"tencent/hy3-preview","slug":"tencent-hy3-preview","name":"Tencent: Hy3 preview","provider":"tencent","contextLength":262144,"pricing":{"inputPerM":0.18,"outputPerM":0.6},"releasedAt":"2026-04-22","huggingFaceId":"tencent/Hy3-preview","profile":{"description":"Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","tools"],"maxOutput":235929,"knowledgeCutoff":null,"cacheReadPerM":0.06,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"tencent/hy3-preview-20260421"}},{"id":"xiaomi/mimo-v2.5-pro","slug":"xiaomi-mimo-v2-5-pro","name":"Xiaomi: MiMo-V2.5-Pro","provider":"xiaomi","contextLength":1050000,"pricing":{"inputPerM":0.435,"outputPerM":0.87},"releasedAt":"2026-04-22","huggingFaceId":"XiaomiMiMo/MiMo-V2.5-Pro","profile":{"description":"MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":131072,"knowledgeCutoff":null,"cacheReadPerM":0.0036,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":"2026-10-21","canonicalSlug":"xiaomi/mimo-v2.5-pro-20260422"}},{"id":"xiaomi/mimo-v2.5","slug":"xiaomi-mimo-v2-5","name":"Xiaomi: MiMo-V2.5","provider":"xiaomi","contextLength":1050000,"pricing":{"inputPerM":0.14,"outputPerM":0.28},"releasedAt":"2026-04-22","huggingFaceId":"XiaomiMiMo/MiMo-V2.5","profile":{"description":"MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...","inputModalities":["text","audio","image","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":131072,"knowledgeCutoff":null,"cacheReadPerM":0.0028,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":"2026-10-21","canonicalSlug":"xiaomi/mimo-v2.5-20260422"}},{"id":"openai/gpt-5.4-image-2","slug":"gpt-5-4-image-2","name":"OpenAI: GPT-5.4 Image 2","provider":"openai","contextLength":272000,"pricing":{"inputPerM":8,"outputPerM":15},"releasedAt":"2026-04-21","huggingFaceId":null,"profile":{"description":"[GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and...","inputModalities":["image","text","file"],"outputModalities":["image","text"],"features":["reasoning","json-mode","structured-outputs"],"maxOutput":128000,"knowledgeCutoff":null,"cacheReadPerM":2,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-5.4-image-2-20260421"}},{"id":"openrouter/pareto-code","slug":"openrouter-pareto-code","name":"Pareto Code Router","provider":"openrouter","contextLength":2000000,"pricing":null,"releasedAt":"2026-04-21","huggingFaceId":null,"profile":{"description":"The Pareto Router maintains a tiered shortlist of strong coding models, ranked by [Artificial Analysis](https://artificialanalysis.ai/) coding percentiles. Set min_coding_score between 0 and 1 on the [pareto-router plugin](https://openrouter.ai/docs/guides/routing/routers/pareto-router#the-min_coding_score-parameter) to control how...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":null,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Router","moderated":false,"expiresAt":null,"canonicalSlug":"openrouter/pareto-code"}},{"id":"moonshotai/kimi-k2.6","slug":"kimi-k2-6","name":"MoonshotAI: Kimi K2.6","provider":"moonshotai","contextLength":262144,"pricing":{"inputPerM":0.65,"outputPerM":3.41},"releasedAt":"2026-04-20","huggingFaceId":"moonshotai/Kimi-K2.6","profile":{"description":"Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...","inputModalities":["text","image"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":235929,"knowledgeCutoff":null,"cacheReadPerM":0.15,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"moonshotai/kimi-k2.6-20260420"}},{"id":"anthropic/claude-opus-4.7","slug":"claude-opus-4-7","name":"Anthropic: Claude Opus 4.7","provider":"anthropic","contextLength":1000000,"pricing":{"inputPerM":5,"outputPerM":25},"releasedAt":"2026-04-16","huggingFaceId":null,"profile":{"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2026-01","cacheReadPerM":0.5,"cacheWritePerM":6.25,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"Claude","moderated":true,"expiresAt":null,"canonicalSlug":"anthropic/claude-4.7-opus-20260416","knowledgeCutoffSource":{"label":"Anthropic model documentation","url":"https://platform.claude.com/docs/en/models/opus-4-7/overview.md"}}},{"id":"z-ai/glm-5.1","slug":"glm-5-1","name":"Z.ai: GLM 5.1","provider":"z-ai","contextLength":204800,"pricing":{"inputPerM":0.966,"outputPerM":3.036},"releasedAt":"2026-04-07","huggingFaceId":"zai-org/GLM-5.1","profile":{"description":"GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":null,"cacheReadPerM":0.1794,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"z-ai/glm-5.1-20260406"}},{"id":"google/gemma-4-26b-a4b-it","slug":"gemma-4-26b-a4b-it","name":"Google: Gemma 4 26B A4B","provider":"google","contextLength":262144,"pricing":{"inputPerM":0.0765,"outputPerM":0.255},"releasedAt":"2026-04-03","huggingFaceId":"google/gemma-4-26B-A4B-it","profile":{"description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference, delivering near-31B quality at...","inputModalities":["image","text","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":235929,"knowledgeCutoff":null,"cacheReadPerM":0.0425,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Gemma","moderated":false,"expiresAt":null,"canonicalSlug":"google/gemma-4-26b-a4b-it-20260403"}},{"id":"google/gemma-4-31b-it","slug":"gemma-4-31b-it","name":"Google: Gemma 4 31B","provider":"google","contextLength":262144,"pricing":{"inputPerM":0.2,"outputPerM":0.4},"releasedAt":"2026-04-02","huggingFaceId":"google/gemma-4-31B-it","profile":{"description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...","inputModalities":["image","text","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":16384,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Gemma","moderated":false,"expiresAt":null,"canonicalSlug":"google/gemma-4-31b-it-20260402"}},{"id":"qwen/qwen3.6-plus","slug":"qwen3-6-plus","name":"Qwen: Qwen3.6 Plus","provider":"qwen","contextLength":1000000,"pricing":{"inputPerM":0.325,"outputPerM":1.95},"releasedAt":"2026-04-02","huggingFaceId":null,"profile":{"description":"Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...","inputModalities":["text","image","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":65536,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":0.40625,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen3","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3.6-plus-04-02"}},{"id":"z-ai/glm-5v-turbo","slug":"glm-5v-turbo","name":"Z.ai: GLM 5V Turbo","provider":"z-ai","contextLength":202752,"pricing":{"inputPerM":1.2,"outputPerM":4},"releasedAt":"2026-04-01","huggingFaceId":null,"profile":{"description":"GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding,...","inputModalities":["image","text","video"],"outputModalities":["text"],"features":["reasoning","json-mode","tools"],"maxOutput":131072,"knowledgeCutoff":null,"cacheReadPerM":0.24,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"z-ai/glm-5v-turbo-20260401"}},{"id":"arcee-ai/trinity-large-thinking","slug":"arcee-ai-trinity-large-thinking","name":"Arcee AI: Trinity Large Thinking","provider":"arcee-ai","contextLength":262144,"pricing":{"inputPerM":0.25,"outputPerM":0.8},"releasedAt":"2026-04-01","huggingFaceId":"arcee-ai/Trinity-Large-Thinking","profile":{"description":"Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks. Launch video: https://youtu.be/Gc82AXLa0Rg?si=4RLn6WBz33qT--B7...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","tools"],"maxOutput":80000,"knowledgeCutoff":null,"cacheReadPerM":0.06,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"arcee-ai/trinity-large-thinking"}},{"id":"x-ai/grok-4.20-multi-agent","slug":"grok-4-20-multi-agent","name":"SpaceXAI: Grok 4.20 Multi-Agent","provider":"x-ai","contextLength":2000000,"pricing":{"inputPerM":1.25,"outputPerM":2.5},"releasedAt":"2026-03-31","huggingFaceId":null,"profile":{"description":"Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs"],"maxOutput":1800000,"knowledgeCutoff":"2025-09-01","cacheReadPerM":0.2,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.005,"tokenizer":"Grok","moderated":false,"expiresAt":null,"canonicalSlug":"x-ai/grok-4.20-multi-agent-20260309"}},{"id":"x-ai/grok-4.20","slug":"grok-4-20","name":"SpaceXAI: Grok 4.20","provider":"x-ai","contextLength":2000000,"pricing":{"inputPerM":1.25,"outputPerM":2.5},"releasedAt":"2026-03-31","huggingFaceId":null,"profile":{"description":"Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":1800000,"knowledgeCutoff":"2025-09-01","cacheReadPerM":0.2,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.005,"tokenizer":"Grok","moderated":false,"expiresAt":null,"canonicalSlug":"x-ai/grok-4.20-20260309"}},{"id":"google/lyria-3-pro-preview","slug":"lyria-3-pro-preview","name":"Google: Lyria 3 Pro Preview","provider":"google","contextLength":1048576,"pricing":{"inputPerM":0,"outputPerM":0},"releasedAt":"2026-03-30","huggingFaceId":null,"profile":{"description":"Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality, 48kHz...","inputModalities":["text","image"],"outputModalities":["text","audio"],"features":["json-mode"],"maxOutput":65536,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"google/lyria-3-pro-preview-20260330"}},{"id":"google/lyria-3-clip-preview","slug":"lyria-3-clip-preview","name":"Google: Lyria 3 Clip Preview","provider":"google","contextLength":1048576,"pricing":{"inputPerM":0,"outputPerM":0},"releasedAt":"2026-03-30","huggingFaceId":null,"profile":{"description":"30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate...","inputModalities":["text","image"],"outputModalities":["text","audio"],"features":["json-mode"],"maxOutput":65536,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"google/lyria-3-clip-preview-20260330"}},{"id":"rekaai/reka-edge","slug":"rekaai-reka-edge","name":"Reka Edge","provider":"rekaai","contextLength":16384,"pricing":{"inputPerM":0.1,"outputPerM":0.1},"releasedAt":"2026-03-20","huggingFaceId":"RekaAI/reka-edge-2603","profile":{"description":"Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding,...","inputModalities":["image","text","video"],"outputModalities":["text"],"features":["structured-outputs","tools"],"maxOutput":14745,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"rekaai/reka-edge-2603"}},{"id":"minimax/minimax-m2.7","slug":"minimax-minimax-m2-7","name":"MiniMax: MiniMax M2.7","provider":"minimax","contextLength":204800,"pricing":{"inputPerM":0.3,"outputPerM":1.2},"releasedAt":"2026-03-18","huggingFaceId":"MiniMaxAI/MiniMax-M2.7","profile":{"description":"MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","tools"],"maxOutput":131072,"knowledgeCutoff":null,"cacheReadPerM":0.06,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"minimax/minimax-m2.7-20260318"}},{"id":"openai/gpt-5.4-nano","slug":"gpt-5-4-nano","name":"OpenAI: GPT-5.4 Nano","provider":"openai","contextLength":400000,"pricing":{"inputPerM":0.2,"outputPerM":1.25},"releasedAt":"2026-03-17","huggingFaceId":null,"profile":{"description":"GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...","inputModalities":["file","image","text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2025-08-31","cacheReadPerM":0.02,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-5.4-nano-20260317"}},{"id":"openai/gpt-5.4-mini","slug":"gpt-5-4-mini","name":"OpenAI: GPT-5.4 Mini","provider":"openai","contextLength":400000,"pricing":{"inputPerM":0.75,"outputPerM":4.5},"releasedAt":"2026-03-17","huggingFaceId":null,"profile":{"description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...","inputModalities":["file","image","text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2025-08-31","cacheReadPerM":0.075,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-5.4-mini-20260317"}},{"id":"mistralai/mistral-small-2603","slug":"mistral-small-2603","name":"Mistral: Mistral Small 4","provider":"mistralai","contextLength":262144,"pricing":{"inputPerM":0.15,"outputPerM":0.6},"releasedAt":"2026-03-16","huggingFaceId":"mistralai/Mistral-Small-4-119B-2603","profile":{"description":"Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...","inputModalities":["text","image"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":209715,"knowledgeCutoff":null,"cacheReadPerM":0.015,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Mistral","moderated":false,"expiresAt":null,"canonicalSlug":"mistralai/mistral-small-2603"}},{"id":"z-ai/glm-5-turbo","slug":"glm-5-turbo","name":"Z.ai: GLM 5 Turbo","provider":"z-ai","contextLength":202752,"pricing":{"inputPerM":1.2,"outputPerM":4},"releasedAt":"2026-03-15","huggingFaceId":null,"profile":{"description":"GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","tools"],"maxOutput":131072,"knowledgeCutoff":null,"cacheReadPerM":0.24,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"z-ai/glm-5-turbo-20260315"}},{"id":"nvidia/nemotron-3-super-120b-a12b","slug":"nvidia-nemotron-3-super-120b-a12b","name":"NVIDIA: Nemotron 3 Super","provider":"nvidia","contextLength":262144,"pricing":{"inputPerM":0.08,"outputPerM":0.45},"releasedAt":"2026-03-11","huggingFaceId":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","profile":{"description":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":235929,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"nvidia/nemotron-3-super-120b-a12b-20230311"}},{"id":"bytedance-seed/seed-2.0-lite","slug":"bytedance-seed-seed-2-0-lite","name":"ByteDance Seed: Seed-2.0-Lite","provider":"bytedance-seed","contextLength":262144,"pricing":{"inputPerM":0.25,"outputPerM":2},"releasedAt":"2026-03-10","huggingFaceId":null,"profile":{"description":"Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latency, making it a practical default choice for most production workloads across...","inputModalities":["text","image","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":131072,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"bytedance-seed/seed-2.0-lite-20260309"}},{"id":"qwen/qwen3.5-9b","slug":"qwen3-5-9b","name":"Qwen: Qwen3.5-9B","provider":"qwen","contextLength":262144,"pricing":{"inputPerM":0.1,"outputPerM":0.15},"releasedAt":"2026-03-10","huggingFaceId":"Qwen/Qwen3.5-9B","profile":{"description":"Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...","inputModalities":["text","image","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":32768,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen3","moderated":false,"expiresAt":"2026-10-21","canonicalSlug":"qwen/qwen3.5-9b-20260310"}},{"id":"openai/gpt-5.4-pro","slug":"gpt-5-4-pro","name":"OpenAI: GPT-5.4 Pro","provider":"openai","contextLength":1050000,"pricing":{"inputPerM":30,"outputPerM":180},"releasedAt":"2026-03-05","huggingFaceId":null,"profile":{"description":"GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2025-08-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-5.4-pro-20260305","knowledgeCutoffSource":{"label":"OpenAI model documentation","url":"https://developers.openai.com/api/docs/models/gpt-5.4-pro.md"}}},{"id":"openai/gpt-5.4","slug":"gpt-5-4","name":"OpenAI: GPT-5.4","provider":"openai","contextLength":1050000,"pricing":{"inputPerM":2.5,"outputPerM":15},"releasedAt":"2026-03-05","huggingFaceId":null,"profile":{"description":"GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2025-08-31","cacheReadPerM":0.25,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-5.4-20260305","knowledgeCutoffSource":{"label":"OpenAI model documentation","url":"https://developers.openai.com/api/docs/models/gpt-5.4.md"}}},{"id":"inception/mercury-2","slug":"inception-mercury-2","name":"Inception: Mercury 2","provider":"inception","contextLength":128000,"pricing":{"inputPerM":0.25,"outputPerM":0.75},"releasedAt":"2026-03-04","huggingFaceId":null,"profile":{"description":"Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":50000,"knowledgeCutoff":null,"cacheReadPerM":0.025,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"inception/mercury-2-20260304"}},{"id":"google/gemini-3.1-flash-lite-preview","slug":"gemini-3-1-flash-lite-preview","name":"Google: Gemini 3.1 Flash Lite Preview","provider":"google","contextLength":1048576,"pricing":{"inputPerM":0.25,"outputPerM":1.5},"releasedAt":"2026-03-03","huggingFaceId":null,"profile":{"description":"Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across...","inputModalities":["text","image","video","file","audio"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":65536,"knowledgeCutoff":null,"cacheReadPerM":0.025,"cacheWritePerM":0.083333,"reasoningPerM":1.5,"webSearchPerRequest":0.014,"tokenizer":"Gemini","moderated":false,"expiresAt":null,"canonicalSlug":"google/gemini-3.1-flash-lite-preview-20260303"}},{"id":"bytedance-seed/seed-2.0-mini","slug":"bytedance-seed-seed-2-0-mini","name":"ByteDance Seed: Seed-2.0-Mini","provider":"bytedance-seed","contextLength":262144,"pricing":{"inputPerM":0.1,"outputPerM":0.4},"releasedAt":"2026-02-26","huggingFaceId":null,"profile":{"description":"Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance comparable to ByteDance-Seed-1.6, supports 256k context, four reasoning effort modes (minimal/low/medium/high), multimodal understanding,...","inputModalities":["text","image","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":131072,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"bytedance-seed/seed-2.0-mini-20260224"}},{"id":"google/gemini-3.1-flash-image-preview","slug":"gemini-3-1-flash-image-preview","name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)","provider":"google","contextLength":65536,"pricing":{"inputPerM":0.5,"outputPerM":3},"releasedAt":"2026-02-26","huggingFaceId":null,"profile":{"description":"Gemini 3.1 Flash Image Preview, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines...","inputModalities":["image","text"],"outputModalities":["image","text"],"features":["reasoning","json-mode","structured-outputs"],"maxOutput":58982,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.014,"tokenizer":"Gemini","moderated":false,"expiresAt":null,"canonicalSlug":"google/gemini-3.1-flash-image-preview-20260226"}},{"id":"qwen/qwen3.5-35b-a3b","slug":"qwen3-5-35b-a3b","name":"Qwen: Qwen3.5-35B-A3B","provider":"qwen","contextLength":262144,"pricing":{"inputPerM":0.15,"outputPerM":1},"releasedAt":"2026-02-25","huggingFaceId":"Qwen/Qwen3.5-35B-A3B","profile":{"description":"The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...","inputModalities":["text","image","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":235929,"knowledgeCutoff":null,"cacheReadPerM":0.05,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen3","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3.5-35b-a3b-20260224"}},{"id":"qwen/qwen3.5-27b","slug":"qwen3-5-27b","name":"Qwen: Qwen3.5-27B","provider":"qwen","contextLength":262144,"pricing":{"inputPerM":0.27,"outputPerM":2.16},"releasedAt":"2026-02-25","huggingFaceId":"Qwen/Qwen3.5-27B","profile":{"description":"The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of...","inputModalities":["text","image","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":65536,"knowledgeCutoff":null,"cacheReadPerM":0.27,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen3","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3.5-27b-20260224"}},{"id":"qwen/qwen3.5-122b-a10b","slug":"qwen3-5-122b-a10b","name":"Qwen: Qwen3.5-122B-A10B","provider":"qwen","contextLength":262144,"pricing":{"inputPerM":0.26,"outputPerM":2.08},"releasedAt":"2026-02-25","huggingFaceId":"Qwen/Qwen3.5-122B-A10B","profile":{"description":"The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...","inputModalities":["text","image","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":65536,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen3","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3.5-122b-a10b-20260224"}},{"id":"qwen/qwen3.5-flash-02-23","slug":"qwen3-5-flash-02-23","name":"Qwen: Qwen3.5-Flash","provider":"qwen","contextLength":1000000,"pricing":{"inputPerM":0.065,"outputPerM":0.26},"releasedAt":"2026-02-25","huggingFaceId":null,"profile":{"description":"The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the...","inputModalities":["text","image","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":65536,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen3","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3.5-flash-20260224"}},{"id":"google/gemini-3.1-pro-preview-customtools","slug":"gemini-3-1-pro-preview-customtools","name":"Google: Gemini 3.1 Pro Preview Custom Tools","provider":"google","contextLength":1048576,"pricing":{"inputPerM":2,"outputPerM":12},"releasedAt":"2026-02-25","huggingFaceId":null,"profile":{"description":"Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party...","inputModalities":["text","audio","image","video","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":65536,"knowledgeCutoff":null,"cacheReadPerM":0.2,"cacheWritePerM":0.375,"reasoningPerM":12,"webSearchPerRequest":0.014,"tokenizer":"Gemini","moderated":false,"expiresAt":null,"canonicalSlug":"google/gemini-3.1-pro-preview-customtools-20260219"}},{"id":"openai/gpt-5.3-codex","slug":"gpt-5-3-codex","name":"OpenAI: GPT-5.3-Codex","provider":"openai","contextLength":400000,"pricing":{"inputPerM":1.75,"outputPerM":14},"releasedAt":"2026-02-24","huggingFaceId":null,"profile":{"description":"GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2025-08-31","cacheReadPerM":0.175,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-5.3-codex-20260224","knowledgeCutoffSource":{"label":"OpenAI model documentation","url":"https://developers.openai.com/api/docs/models/gpt-5.3-codex.md"}}},{"id":"aion-labs/aion-2.0","slug":"aion-labs-aion-2-0","name":"AionLabs: Aion-2.0","provider":"aion-labs","contextLength":131072,"pricing":{"inputPerM":0.8,"outputPerM":1.6},"releasedAt":"2026-02-23","huggingFaceId":null,"profile":{"description":"Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, making narratives feel more engaging....","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","tools"],"maxOutput":32768,"knowledgeCutoff":null,"cacheReadPerM":0.2,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"aion-labs/aion-2.0-20260223"}},{"id":"google/gemini-3.1-pro-preview","slug":"gemini-3-1-pro-preview","name":"Google: Gemini 3.1 Pro Preview","provider":"google","contextLength":1048576,"pricing":{"inputPerM":2,"outputPerM":12},"releasedAt":"2026-02-19","huggingFaceId":null,"profile":{"description":"Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...","inputModalities":["audio","file","image","text","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":65536,"knowledgeCutoff":null,"cacheReadPerM":0.2,"cacheWritePerM":0.375,"reasoningPerM":12,"webSearchPerRequest":0.014,"tokenizer":"Gemini","moderated":false,"expiresAt":null,"canonicalSlug":"google/gemini-3.1-pro-preview-20260219"}},{"id":"anthropic/claude-sonnet-4.6","slug":"claude-sonnet-4-6","name":"Anthropic: Claude Sonnet 4.6","provider":"anthropic","contextLength":1000000,"pricing":{"inputPerM":3,"outputPerM":15},"releasedAt":"2026-02-17","huggingFaceId":null,"profile":{"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2025-08","cacheReadPerM":0.3,"cacheWritePerM":3.75,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"Claude","moderated":true,"expiresAt":null,"canonicalSlug":"anthropic/claude-4.6-sonnet-20260217","knowledgeCutoffSource":{"label":"Anthropic model documentation","url":"https://platform.claude.com/docs/en/models/sonnet-4-6/overview.md"}}},{"id":"qwen/qwen3.5-plus-02-15","slug":"qwen3-5-plus-02-15","name":"Qwen: Qwen3.5 Plus 2026-02-15","provider":"qwen","contextLength":1000000,"pricing":{"inputPerM":0.26,"outputPerM":1.56},"releasedAt":"2026-02-16","huggingFaceId":null,"profile":{"description":"The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of...","inputModalities":["text","image","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":65536,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen3","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3.5-plus-20260216"}},{"id":"qwen/qwen3.5-397b-a17b","slug":"qwen3-5-397b-a17b","name":"Qwen: Qwen3.5 397B A17B","provider":"qwen","contextLength":262144,"pricing":{"inputPerM":0.39,"outputPerM":2.34},"releasedAt":"2026-02-16","huggingFaceId":"Qwen/Qwen3.5-397B-A17B","profile":{"description":"The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...","inputModalities":["text","image","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":65536,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen3","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3.5-397b-a17b-20260216"}},{"id":"minimax/minimax-m2.5","slug":"minimax-minimax-m2-5","name":"MiniMax: MiniMax M2.5","provider":"minimax","contextLength":204800,"pricing":{"inputPerM":0.27,"outputPerM":0.95},"releasedAt":"2026-02-12","huggingFaceId":"MiniMaxAI/MiniMax-M2.5","profile":{"description":"MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":32768,"knowledgeCutoff":null,"cacheReadPerM":0.03,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"minimax/minimax-m2.5-20260211"}},{"id":"z-ai/glm-5","slug":"glm-5","name":"Z.ai: GLM 5","provider":"z-ai","contextLength":204800,"pricing":{"inputPerM":0.6,"outputPerM":1.92},"releasedAt":"2026-02-11","huggingFaceId":"zai-org/GLM-5","profile":{"description":"GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":null,"cacheReadPerM":0.12,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"z-ai/glm-5-20260211"}},{"id":"anthropic/claude-opus-4.6","slug":"claude-opus-4-6","name":"Anthropic: Claude Opus 4.6","provider":"anthropic","contextLength":1000000,"pricing":{"inputPerM":5,"outputPerM":25},"releasedAt":"2026-02-04","huggingFaceId":null,"profile":{"description":"Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2025-05","cacheReadPerM":0.5,"cacheWritePerM":6.25,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"Claude","moderated":true,"expiresAt":null,"canonicalSlug":"anthropic/claude-4.6-opus-20260205","knowledgeCutoffSource":{"label":"Anthropic model documentation","url":"https://platform.claude.com/docs/en/models/opus-4-6/overview.md"}}},{"id":"qwen/qwen3-coder-next","slug":"qwen3-coder-next","name":"Qwen: Qwen3 Coder Next","provider":"qwen","contextLength":262144,"pricing":{"inputPerM":0.12,"outputPerM":0.8},"releasedAt":"2026-02-04","huggingFaceId":"Qwen/Qwen3-Coder-Next","profile":{"description":"Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":235929,"knowledgeCutoff":null,"cacheReadPerM":0.07,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3-coder-next-2025-02-03"}},{"id":"openrouter/free","slug":"openrouter-free","name":"Free Models Router","provider":"openrouter","contextLength":200000,"pricing":{"inputPerM":0,"outputPerM":0},"releasedAt":"2026-02-01","huggingFaceId":null,"profile":{"description":"The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenRouter. The router smartly filters for models that...","inputModalities":["text","image"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":null,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Router","moderated":false,"expiresAt":null,"canonicalSlug":"openrouter/free"}},{"id":"stepfun/step-3.5-flash","slug":"stepfun-step-3-5-flash","name":"StepFun: Step 3.5 Flash","provider":"stepfun","contextLength":262144,"pricing":{"inputPerM":0.1,"outputPerM":0.3},"releasedAt":"2026-01-29","huggingFaceId":"stepfun-ai/Step-3.5-Flash","profile":{"description":"Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","tools"],"maxOutput":65536,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"stepfun/step-3.5-flash"}},{"id":"moonshotai/kimi-k2.5","slug":"kimi-k2-5","name":"MoonshotAI: Kimi K2.5","provider":"moonshotai","contextLength":262144,"pricing":{"inputPerM":0.5,"outputPerM":2.5},"releasedAt":"2026-01-27","huggingFaceId":"moonshotai/Kimi-K2.5","profile":{"description":"Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...","inputModalities":["text","image"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":235929,"knowledgeCutoff":null,"cacheReadPerM":0.15,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"moonshotai/kimi-k2.5-0127"}},{"id":"upstage/solar-pro-3","slug":"upstage-solar-pro-3","name":"Upstage: Solar Pro 3","provider":"upstage","contextLength":131072,"pricing":{"inputPerM":0.15,"outputPerM":0.6},"releasedAt":"2026-01-27","huggingFaceId":null,"profile":{"description":"Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model. With 102B total parameters and 12B active parameters per forward pass, it delivers exceptional performance while maintaining computational efficiency. Optimized...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":117964,"knowledgeCutoff":null,"cacheReadPerM":0.015,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"upstage/solar-pro-3"}},{"id":"minimax/minimax-m2-her","slug":"minimax-minimax-m2-her","name":"MiniMax: MiniMax M2-her","provider":"minimax","contextLength":65536,"pricing":{"inputPerM":0.3,"outputPerM":1.2},"releasedAt":"2026-01-23","huggingFaceId":null,"profile":{"description":"MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message...","inputModalities":["text"],"outputModalities":["text"],"features":[],"maxOutput":2048,"knowledgeCutoff":null,"cacheReadPerM":0.03,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"minimax/minimax-m2-her-20260123"}},{"id":"writer/palmyra-x5","slug":"writer-palmyra-x5","name":"Writer: Palmyra X5","provider":"writer","contextLength":1040000,"pricing":{"inputPerM":0.6,"outputPerM":6},"releasedAt":"2026-01-21","huggingFaceId":null,"profile":{"description":"Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context windows up to 1 million...","inputModalities":["text"],"outputModalities":["text"],"features":[],"maxOutput":8192,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":true,"expiresAt":null,"canonicalSlug":"writer/palmyra-x5-20250428"}},{"id":"openai/gpt-audio","slug":"gpt-audio","name":"OpenAI: GPT Audio","provider":"openai","contextLength":128000,"pricing":{"inputPerM":2.5,"outputPerM":10},"releasedAt":"2026-01-19","huggingFaceId":null,"profile":{"description":"The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced...","inputModalities":["text","audio"],"outputModalities":["text","audio"],"features":["json-mode","structured-outputs","tools"],"maxOutput":16384,"knowledgeCutoff":"2023-10-01","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-audio","knowledgeCutoffSource":{"label":"OpenAI model documentation","url":"https://developers.openai.com/api/docs/models/gpt-audio.md"}}},{"id":"openai/gpt-audio-mini","slug":"gpt-audio-mini","name":"OpenAI: GPT Audio Mini","provider":"openai","contextLength":128000,"pricing":{"inputPerM":0.6,"outputPerM":2.4},"releasedAt":"2026-01-19","huggingFaceId":null,"profile":{"description":"A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0.60 per million...","inputModalities":["text","audio"],"outputModalities":["text","audio"],"features":["json-mode","structured-outputs","tools"],"maxOutput":16384,"knowledgeCutoff":"2023-10-01","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-audio-mini","knowledgeCutoffSource":{"label":"OpenAI model documentation","url":"https://developers.openai.com/api/docs/models/gpt-audio-mini.md"}}},{"id":"z-ai/glm-4.7-flash","slug":"glm-4-7-flash","name":"Z.ai: GLM 4.7 Flash","provider":"z-ai","contextLength":200000,"pricing":{"inputPerM":0.0605,"outputPerM":0.4},"releasedAt":"2026-01-19","huggingFaceId":"zai-org/GLM-4.7-Flash","profile":{"description":"As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":117964,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"z-ai/glm-4.7-flash-20260119"}},{"id":"openai/gpt-5.2-codex","slug":"gpt-5-2-codex","name":"OpenAI: GPT-5.2-Codex","provider":"openai","contextLength":400000,"pricing":{"inputPerM":1.75,"outputPerM":14},"releasedAt":"2026-01-14","huggingFaceId":null,"profile":{"description":"GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....","inputModalities":["text","image"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2025-08-31","cacheReadPerM":0.175,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":false,"expiresAt":null,"canonicalSlug":"openai/gpt-5.2-codex-20260114","knowledgeCutoffSource":{"label":"OpenAI model documentation","url":"https://developers.openai.com/api/docs/models/gpt-5.2-codex.md"}}},{"id":"bytedance-seed/seed-1.6-flash","slug":"bytedance-seed-seed-1-6-flash","name":"ByteDance Seed: Seed 1.6 Flash","provider":"bytedance-seed","contextLength":262144,"pricing":{"inputPerM":0.075,"outputPerM":0.3},"releasedAt":"2025-12-23","huggingFaceId":null,"profile":{"description":"Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a 256k context window and can generate outputs of...","inputModalities":["image","text","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":32768,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":"2026-11-11","canonicalSlug":"bytedance-seed/seed-1.6-flash-20250625"}},{"id":"bytedance-seed/seed-1.6","slug":"bytedance-seed-seed-1-6","name":"ByteDance Seed: Seed 1.6","provider":"bytedance-seed","contextLength":262144,"pricing":{"inputPerM":0.25,"outputPerM":2},"releasedAt":"2025-12-23","huggingFaceId":null,"profile":{"description":"Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window.","inputModalities":["image","text","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":32768,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":"2026-11-11","canonicalSlug":"bytedance-seed/seed-1.6-20250625"}},{"id":"minimax/minimax-m2.1","slug":"minimax-minimax-m2-1","name":"MiniMax: MiniMax M2.1","provider":"minimax","contextLength":204800,"pricing":{"inputPerM":0.3,"outputPerM":1.2},"releasedAt":"2025-12-23","huggingFaceId":"MiniMaxAI/MiniMax-M2.1","profile":{"description":"MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","tools"],"maxOutput":131072,"knowledgeCutoff":null,"cacheReadPerM":0.03,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"minimax/minimax-m2.1"}},{"id":"z-ai/glm-4.7","slug":"glm-4-7","name":"Z.ai: GLM 4.7","provider":"z-ai","contextLength":204800,"pricing":{"inputPerM":0.54,"outputPerM":1.98},"releasedAt":"2025-12-22","huggingFaceId":"zai-org/GLM-4.7","profile":{"description":"GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":131072,"knowledgeCutoff":null,"cacheReadPerM":0.099,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"z-ai/glm-4.7-20251222"}},{"id":"google/gemini-3-flash-preview","slug":"gemini-3-flash-preview","name":"Google: Gemini 3 Flash Preview","provider":"google","contextLength":1048576,"pricing":{"inputPerM":0.5,"outputPerM":3},"releasedAt":"2025-12-17","huggingFaceId":null,"profile":{"description":"Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...","inputModalities":["text","image","file","audio","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":65536,"knowledgeCutoff":null,"cacheReadPerM":0.05,"cacheWritePerM":0.083333,"reasoningPerM":3,"webSearchPerRequest":0.014,"tokenizer":"Gemini","moderated":false,"expiresAt":null,"canonicalSlug":"google/gemini-3-flash-preview-20251217"}},{"id":"nvidia/nemotron-3-nano-30b-a3b","slug":"nvidia-nemotron-3-nano-30b-a3b","name":"NVIDIA: Nemotron 3 Nano 30B A3B","provider":"nvidia","contextLength":262144,"pricing":{"inputPerM":0.06,"outputPerM":0.24},"releasedAt":"2025-12-14","huggingFaceId":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","profile":{"description":"NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":235929,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"nvidia/nemotron-3-nano-30b-a3b"}},{"id":"openai/gpt-5.2-chat","slug":"gpt-5-2-chat","name":"OpenAI: GPT-5.2 Chat","provider":"openai","contextLength":128000,"pricing":{"inputPerM":1.75,"outputPerM":14},"releasedAt":"2025-12-10","huggingFaceId":null,"profile":{"description":"GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on...","inputModalities":["file","image","text"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":32000,"knowledgeCutoff":null,"cacheReadPerM":0.175,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":false,"expiresAt":null,"canonicalSlug":"openai/gpt-5.2-chat-20251211"}},{"id":"openai/gpt-5.2-pro","slug":"gpt-5-2-pro","name":"OpenAI: GPT-5.2 Pro","provider":"openai","contextLength":400000,"pricing":{"inputPerM":21,"outputPerM":168},"releasedAt":"2025-12-10","huggingFaceId":null,"profile":{"description":"GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...","inputModalities":["image","text","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2025-08-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-5.2-pro-20251211","knowledgeCutoffSource":{"label":"OpenAI model documentation","url":"https://developers.openai.com/api/docs/models/gpt-5.2-pro.md"}}},{"id":"openai/gpt-5.2","slug":"gpt-5-2","name":"OpenAI: GPT-5.2","provider":"openai","contextLength":400000,"pricing":{"inputPerM":1.75,"outputPerM":14},"releasedAt":"2025-12-10","huggingFaceId":null,"profile":{"description":"GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...","inputModalities":["file","image","text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2025-08-31","cacheReadPerM":0.175,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-5.2-20251211","knowledgeCutoffSource":{"label":"OpenAI model documentation","url":"https://developers.openai.com/api/docs/models/gpt-5.2.md"}}},{"id":"mistralai/devstral-2512","slug":"devstral-2512","name":"Mistral: Devstral 2 2512","provider":"mistralai","contextLength":262144,"pricing":{"inputPerM":0.4,"outputPerM":2},"releasedAt":"2025-12-09","huggingFaceId":"mistralai/Devstral-2-123B-Instruct-2512","profile":{"description":"Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...","inputModalities":["text","file"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":209715,"knowledgeCutoff":null,"cacheReadPerM":0.04,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Mistral","moderated":false,"expiresAt":null,"canonicalSlug":"mistralai/devstral-2512"}},{"id":"relace/relace-search","slug":"relace-relace-search","name":"Relace: Relace Search","provider":"relace","contextLength":256000,"pricing":{"inputPerM":1,"outputPerM":3},"releasedAt":"2025-12-08","huggingFaceId":null,"profile":{"description":"The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search performs agentic...","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","tools"],"maxOutput":128000,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"relace/relace-search-20251208"}},{"id":"z-ai/glm-4.6v","slug":"glm-4-6v","name":"Z.ai: GLM 4.6V","provider":"z-ai","contextLength":131072,"pricing":{"inputPerM":0.3,"outputPerM":0.9},"releasedAt":"2025-12-08","huggingFaceId":"zai-org/GLM-4.6V","profile":{"description":"GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts...","inputModalities":["image","text","video"],"outputModalities":["text"],"features":["reasoning","json-mode","tools"],"maxOutput":32768,"knowledgeCutoff":null,"cacheReadPerM":0.055,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"z-ai/glm-4.6-20251208"}},{"id":"openrouter/bodybuilder","slug":"openrouter-bodybuilder","name":"Body Builder (beta)","provider":"openrouter","contextLength":128000,"pricing":null,"releasedAt":"2025-12-05","huggingFaceId":null,"profile":{"description":"Transform your natural language requests into structured OpenRouter API request objects. Describe what you want to accomplish with AI models, and Body Builder will construct the appropriate API calls. Example:...","inputModalities":["text"],"outputModalities":["text"],"features":[],"maxOutput":null,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Router","moderated":false,"expiresAt":null,"canonicalSlug":"openrouter/bodybuilder"}},{"id":"openai/gpt-5.1-codex-max","slug":"gpt-5-1-codex-max","name":"OpenAI: GPT-5.1-Codex-Max","provider":"openai","contextLength":400000,"pricing":{"inputPerM":1.25,"outputPerM":10},"releasedAt":"2025-12-04","huggingFaceId":null,"profile":{"description":"GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic...","inputModalities":["text","image"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2024-09-30","cacheReadPerM":0.125,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":false,"expiresAt":null,"canonicalSlug":"openai/gpt-5.1-codex-max-20251204","knowledgeCutoffSource":{"label":"OpenAI model documentation","url":"https://developers.openai.com/api/docs/models/gpt-5.1-codex-max.md"}}},{"id":"amazon/nova-2-lite-v1","slug":"amazon-nova-2-lite-v1","name":"Amazon: Nova 2 Lite","provider":"amazon","contextLength":1000000,"pricing":{"inputPerM":0.3,"outputPerM":2.5},"releasedAt":"2025-12-02","huggingFaceId":null,"profile":{"description":"Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing...","inputModalities":["text","image","video","file"],"outputModalities":["text"],"features":["reasoning","tools"],"maxOutput":65535,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Nova","moderated":true,"expiresAt":null,"canonicalSlug":"amazon/nova-2-lite-v1"}},{"id":"mistralai/ministral-14b-2512","slug":"ministral-14b-2512","name":"Mistral: Ministral 3 14B 2512","provider":"mistralai","contextLength":262144,"pricing":{"inputPerM":0.2,"outputPerM":0.2},"releasedAt":"2025-12-02","huggingFaceId":"mistralai/Ministral-3-14B-Instruct-2512","profile":{"description":"The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...","inputModalities":["text","image"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":209715,"knowledgeCutoff":null,"cacheReadPerM":0.02,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Mistral","moderated":false,"expiresAt":null,"canonicalSlug":"mistralai/ministral-14b-2512"}},{"id":"mistralai/ministral-8b-2512","slug":"ministral-8b-2512","name":"Mistral: Ministral 3 8B 2512","provider":"mistralai","contextLength":262144,"pricing":{"inputPerM":0.15,"outputPerM":0.15},"releasedAt":"2025-12-02","huggingFaceId":"mistralai/Ministral-3-8B-Instruct-2512","profile":{"description":"A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.","inputModalities":["text","image"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":209715,"knowledgeCutoff":null,"cacheReadPerM":0.015,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Mistral","moderated":false,"expiresAt":null,"canonicalSlug":"mistralai/ministral-8b-2512"}},{"id":"mistralai/ministral-3b-2512","slug":"ministral-3b-2512","name":"Mistral: Ministral 3 3B 2512","provider":"mistralai","contextLength":131072,"pricing":{"inputPerM":0.1,"outputPerM":0.1},"releasedAt":"2025-12-02","huggingFaceId":"mistralai/Ministral-3-3B-Instruct-2512","profile":{"description":"The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.","inputModalities":["text","image"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":104857,"knowledgeCutoff":null,"cacheReadPerM":0.01,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Mistral","moderated":false,"expiresAt":null,"canonicalSlug":"mistralai/ministral-3b-2512"}},{"id":"mistralai/mistral-large-2512","slug":"mistral-large-2512","name":"Mistral: Mistral Large 3 2512","provider":"mistralai","contextLength":262144,"pricing":{"inputPerM":0.5,"outputPerM":1.5},"releasedAt":"2025-12-01","huggingFaceId":null,"profile":{"description":"Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":209715,"knowledgeCutoff":null,"cacheReadPerM":0.05,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Mistral","moderated":false,"expiresAt":null,"canonicalSlug":"mistralai/mistral-large-2512"}},{"id":"deepseek/deepseek-v3.2","slug":"deepseek-v3-2","name":"DeepSeek: DeepSeek V3.2","provider":"deepseek","contextLength":163840,"pricing":{"inputPerM":0.28,"outputPerM":0.42},"releasedAt":"2025-12-01","huggingFaceId":"deepseek-ai/DeepSeek-V3.2","profile":{"description":"DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":65536,"knowledgeCutoff":null,"cacheReadPerM":0.028,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"DeepSeek","moderated":false,"expiresAt":null,"canonicalSlug":"deepseek/deepseek-v3.2-20251201"}},{"id":"anthropic/claude-opus-4.5","slug":"claude-opus-4-5","name":"Anthropic: Claude Opus 4.5","provider":"anthropic","contextLength":200000,"pricing":{"inputPerM":5,"outputPerM":25},"releasedAt":"2025-11-24","huggingFaceId":null,"profile":{"description":"Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...","inputModalities":["file","image","text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":64000,"knowledgeCutoff":"2025-05","cacheReadPerM":0.5,"cacheWritePerM":6.25,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"Claude","moderated":true,"expiresAt":null,"canonicalSlug":"anthropic/claude-4.5-opus-20251124","knowledgeCutoffSource":{"label":"Anthropic model documentation","url":"https://platform.claude.com/docs/en/models/opus-4-5/overview.md"}}},{"id":"google/gemini-3-pro-image-preview","slug":"gemini-3-pro-image-preview","name":"Google: Nano Banana Pro (Gemini 3 Pro Image Preview)","provider":"google","contextLength":65536,"pricing":{"inputPerM":2,"outputPerM":12},"releasedAt":"2025-11-20","huggingFaceId":null,"profile":{"description":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...","inputModalities":["image","text"],"outputModalities":["image","text"],"features":["reasoning","json-mode","structured-outputs"],"maxOutput":32768,"knowledgeCutoff":null,"cacheReadPerM":0.2,"cacheWritePerM":0.375,"reasoningPerM":12,"webSearchPerRequest":0.014,"tokenizer":"Gemini","moderated":false,"expiresAt":null,"canonicalSlug":"google/gemini-3-pro-image-preview-20251120"}},{"id":"openai/gpt-5.1","slug":"gpt-5-1","name":"OpenAI: GPT-5.1","provider":"openai","contextLength":400000,"pricing":{"inputPerM":1.25,"outputPerM":10},"releasedAt":"2025-11-13","huggingFaceId":null,"profile":{"description":"GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...","inputModalities":["image","text","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2024-09-30","cacheReadPerM":0.125,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-5.1-20251113","knowledgeCutoffSource":{"label":"OpenAI model documentation","url":"https://developers.openai.com/api/docs/models/gpt-5.1.md"}}},{"id":"openai/gpt-5.1-codex","slug":"gpt-5-1-codex","name":"OpenAI: GPT-5.1-Codex","provider":"openai","contextLength":400000,"pricing":{"inputPerM":1.25,"outputPerM":10},"releasedAt":"2025-11-13","huggingFaceId":null,"profile":{"description":"GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....","inputModalities":["text","image"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2024-09-30","cacheReadPerM":0.13,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":false,"expiresAt":null,"canonicalSlug":"openai/gpt-5.1-codex-20251113","knowledgeCutoffSource":{"label":"OpenAI model documentation","url":"https://developers.openai.com/api/docs/models/gpt-5.1-codex.md"}}},{"id":"openai/gpt-5.1-codex-mini","slug":"gpt-5-1-codex-mini","name":"OpenAI: GPT-5.1-Codex-Mini","provider":"openai","contextLength":400000,"pricing":{"inputPerM":0.25,"outputPerM":2},"releasedAt":"2025-11-13","huggingFaceId":null,"profile":{"description":"GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex","inputModalities":["image","text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2024-09-30","cacheReadPerM":0.03,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":false,"expiresAt":null,"canonicalSlug":"openai/gpt-5.1-codex-mini-20251113","knowledgeCutoffSource":{"label":"OpenAI model documentation","url":"https://developers.openai.com/api/docs/models/gpt-5.1-codex-mini.md"}}},{"id":"moonshotai/kimi-k2-thinking","slug":"kimi-k2-thinking","name":"MoonshotAI: Kimi K2 Thinking","provider":"moonshotai","contextLength":262144,"pricing":{"inputPerM":0.6,"outputPerM":2.5},"releasedAt":"2025-11-06","huggingFaceId":"moonshotai/Kimi-K2-Thinking","profile":{"description":"Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":98304,"knowledgeCutoff":null,"cacheReadPerM":0.15,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"moonshotai/kimi-k2-thinking-20251106"}},{"id":"amazon/nova-premier-v1","slug":"amazon-nova-premier-v1","name":"Amazon: Nova Premier 1.0","provider":"amazon","contextLength":1000000,"pricing":{"inputPerM":2.5,"outputPerM":12.5},"releasedAt":"2025-10-31","huggingFaceId":null,"profile":{"description":"Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.","inputModalities":["text","image"],"outputModalities":["text"],"features":["tools"],"maxOutput":32000,"knowledgeCutoff":null,"cacheReadPerM":0.625,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Nova","moderated":true,"expiresAt":null,"canonicalSlug":"amazon/nova-premier-v1"}},{"id":"perplexity/sonar-pro-search","slug":"perplexity-sonar-pro-search","name":"Perplexity: Sonar Pro Search","provider":"perplexity","contextLength":200000,"pricing":{"inputPerM":3,"outputPerM":15},"releasedAt":"2025-10-30","huggingFaceId":null,"profile":{"description":"Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based...","inputModalities":["text","image"],"outputModalities":["text"],"features":["reasoning","structured-outputs","web-search"],"maxOutput":8000,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.018,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"perplexity/sonar-pro-search"}},{"id":"mistralai/voxtral-small-24b-2507","slug":"voxtral-small-24b-2507","name":"Mistral: Voxtral Small 24B 2507","provider":"mistralai","contextLength":32768,"pricing":{"inputPerM":0.1,"outputPerM":0.3},"releasedAt":"2025-10-30","huggingFaceId":"mistralai/Voxtral-Small-24B-2507","profile":{"description":"Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio...","inputModalities":["text","audio","file"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":26214,"knowledgeCutoff":null,"cacheReadPerM":0.01,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Mistral","moderated":false,"expiresAt":null,"canonicalSlug":"mistralai/voxtral-small-24b-2507"}},{"id":"openai/gpt-oss-safeguard-20b","slug":"gpt-oss-safeguard-20b","name":"OpenAI: gpt-oss-safeguard-20b","provider":"openai","contextLength":131072,"pricing":{"inputPerM":0.075,"outputPerM":0.3},"releasedAt":"2025-10-29","huggingFaceId":"openai/gpt-oss-safeguard-20b","profile":{"description":"gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":65536,"knowledgeCutoff":null,"cacheReadPerM":0.0375,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"GPT","moderated":false,"expiresAt":null,"canonicalSlug":"openai/gpt-oss-safeguard-20b"}},{"id":"minimax/minimax-m2","slug":"minimax-minimax-m2","name":"MiniMax: MiniMax M2","provider":"minimax","contextLength":204800,"pricing":{"inputPerM":0.255,"outputPerM":1.02},"releasedAt":"2025-10-23","huggingFaceId":"MiniMaxAI/MiniMax-M2","profile":{"description":"MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":131072,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"minimax/minimax-m2"}},{"id":"ibm-granite/granite-4.0-h-micro","slug":"ibm-granite-granite-4-0-h-micro","name":"IBM: Granite 4.0 Micro","provider":"ibm-granite","contextLength":131000,"pricing":{"inputPerM":0.017,"outputPerM":0.112},"releasedAt":"2025-10-20","huggingFaceId":"ibm-granite/granite-4.0-h-micro","profile":{"description":"Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM. They are fine-tuned for long...","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode"],"maxOutput":117900,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"ibm-granite/granite-4.0-h-micro"}},{"id":"openai/gpt-5-image-mini","slug":"gpt-5-image-mini","name":"OpenAI: GPT-5 Image Mini","provider":"openai","contextLength":400000,"pricing":{"inputPerM":2.5,"outputPerM":2},"releasedAt":"2025-10-16","huggingFaceId":null,"profile":{"description":"GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text...","inputModalities":["file","image","text"],"outputModalities":["image","text"],"features":["reasoning","json-mode","structured-outputs"],"maxOutput":128000,"knowledgeCutoff":null,"cacheReadPerM":0.25,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-5-image-mini"}},{"id":"anthropic/claude-haiku-4.5","slug":"claude-haiku-4-5","name":"Anthropic: Claude Haiku 4.5","provider":"anthropic","contextLength":200000,"pricing":{"inputPerM":1,"outputPerM":5},"releasedAt":"2025-10-15","huggingFaceId":null,"profile":{"description":"Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":64000,"knowledgeCutoff":"2025-02","cacheReadPerM":0.1,"cacheWritePerM":1.25,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"Claude","moderated":true,"expiresAt":null,"canonicalSlug":"anthropic/claude-4.5-haiku-20251001","knowledgeCutoffSource":{"label":"Anthropic model documentation","url":"https://platform.claude.com/docs/en/models/haiku-4-5/overview.md"}}},{"id":"qwen/qwen3-vl-8b-instruct","slug":"qwen3-vl-8b-instruct","name":"Qwen: Qwen3 VL 8B Instruct","provider":"qwen","contextLength":262144,"pricing":{"inputPerM":0.25,"outputPerM":0.75},"releasedAt":"2025-10-14","huggingFaceId":"Qwen/Qwen3-VL-8B-Instruct","profile":{"description":"Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon...","inputModalities":["image","text"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":235929,"knowledgeCutoff":null,"cacheReadPerM":0.12,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen3","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3-vl-8b-instruct"}},{"id":"openai/gpt-5-image","slug":"gpt-5-image","name":"OpenAI: GPT-5 Image","provider":"openai","contextLength":400000,"pricing":{"inputPerM":10,"outputPerM":10},"releasedAt":"2025-10-14","huggingFaceId":null,"profile":{"description":"[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following,...","inputModalities":["image","text","file"],"outputModalities":["image","text"],"features":["reasoning","json-mode","structured-outputs"],"maxOutput":128000,"knowledgeCutoff":null,"cacheReadPerM":1.25,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-5-image"}},{"id":"google/gemini-2.5-flash-image","slug":"gemini-2-5-flash-image","name":"Google: Nano Banana (Gemini 2.5 Flash Image)","provider":"google","contextLength":32768,"pricing":{"inputPerM":0.3,"outputPerM":2.5},"releasedAt":"2025-10-07","huggingFaceId":null,"profile":{"description":"Gemini 2.5 Flash Image, a.k.a. \"Nano Banana,\" is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation,...","inputModalities":["image","text"],"outputModalities":["image","text"],"features":["json-mode","structured-outputs"],"maxOutput":8192,"knowledgeCutoff":"2025-01-31","cacheReadPerM":0.03,"cacheWritePerM":0.083333,"reasoningPerM":2.5,"webSearchPerRequest":0.014,"tokenizer":"Gemini","moderated":false,"expiresAt":null,"canonicalSlug":"google/gemini-2.5-flash-image"}},{"id":"qwen/qwen3-vl-30b-a3b-thinking","slug":"qwen3-vl-30b-a3b-thinking","name":"Qwen: Qwen3 VL 30B A3B Thinking","provider":"qwen","contextLength":262144,"pricing":{"inputPerM":0.29,"outputPerM":1},"releasedAt":"2025-10-06","huggingFaceId":"Qwen/Qwen3-VL-30B-A3B-Thinking","profile":{"description":"Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels...","inputModalities":["text","image"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":235929,"knowledgeCutoff":"2025-03-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen3","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3-vl-30b-a3b-thinking"}},{"id":"qwen/qwen3-vl-30b-a3b-instruct","slug":"qwen3-vl-30b-a3b-instruct","name":"Qwen: Qwen3 VL 30B A3B Instruct","provider":"qwen","contextLength":262144,"pricing":{"inputPerM":0.15,"outputPerM":0.6},"releasedAt":"2025-10-06","huggingFaceId":"Qwen/Qwen3-VL-30B-A3B-Instruct","profile":{"description":"Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...","inputModalities":["text","image"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":16384,"knowledgeCutoff":"2025-03-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen3","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3-vl-30b-a3b-instruct"}},{"id":"openai/gpt-5-pro","slug":"gpt-5-pro","name":"OpenAI: GPT-5 Pro","provider":"openai","contextLength":400000,"pricing":{"inputPerM":15,"outputPerM":120},"releasedAt":"2025-10-06","huggingFaceId":null,"profile":{"description":"GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...","inputModalities":["image","text","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2024-09-30","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-5-pro-2025-10-06"}},{"id":"z-ai/glm-4.6","slug":"glm-4-6","name":"Z.ai: GLM 4.6","provider":"z-ai","contextLength":204800,"pricing":{"inputPerM":0.55,"outputPerM":2.2},"releasedAt":"2025-09-30","huggingFaceId":"zai-org/GLM-4.6","profile":{"description":"Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":131072,"knowledgeCutoff":"2025-03-31","cacheReadPerM":0.11,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"z-ai/glm-4.6"}},{"id":"anthropic/claude-sonnet-4.5","slug":"claude-sonnet-4-5","name":"Anthropic: Claude Sonnet 4.5","provider":"anthropic","contextLength":1000000,"pricing":{"inputPerM":3,"outputPerM":15},"releasedAt":"2025-09-29","huggingFaceId":null,"profile":{"description":"Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":64000,"knowledgeCutoff":"2025-01-31","cacheReadPerM":0.3,"cacheWritePerM":3.75,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"Claude","moderated":true,"expiresAt":null,"canonicalSlug":"anthropic/claude-4.5-sonnet-20250929"}},{"id":"deepseek/deepseek-v3.2-exp","slug":"deepseek-v3-2-exp","name":"DeepSeek: DeepSeek V3.2 Exp","provider":"deepseek","contextLength":163840,"pricing":{"inputPerM":0.27,"outputPerM":0.41},"releasedAt":"2025-09-29","huggingFaceId":"deepseek-ai/DeepSeek-V3.2-Exp","profile":{"description":"DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":147456,"knowledgeCutoff":"2025-07-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"DeepSeek","moderated":false,"expiresAt":null,"canonicalSlug":"deepseek/deepseek-v3.2-exp"}},{"id":"thedrummer/cydonia-24b-v4.1","slug":"thedrummer-cydonia-24b-v4-1","name":"TheDrummer: Cydonia 24B V4.1","provider":"thedrummer","contextLength":131072,"pricing":{"inputPerM":0.3,"outputPerM":0.5},"releasedAt":"2025-09-27","huggingFaceId":"thedrummer/cydonia-24b-v4.1","profile":{"description":"Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs"],"maxOutput":117964,"knowledgeCutoff":"2024-04-30","cacheReadPerM":0.15,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"thedrummer/cydonia-24b-v4.1"}},{"id":"relace/relace-apply-3","slug":"relace-relace-apply-3","name":"Relace: Relace Apply 3","provider":"relace","contextLength":256000,"pricing":{"inputPerM":0.85,"outputPerM":1.25},"releasedAt":"2025-09-26","huggingFaceId":null,"profile":{"description":"Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at...","inputModalities":["text"],"outputModalities":["text"],"features":[],"maxOutput":128000,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"relace/relace-apply-3"}},{"id":"qwen/qwen3-vl-235b-a22b-instruct","slug":"qwen3-vl-235b-a22b-instruct","name":"Qwen: Qwen3 VL 235B A22B Instruct","provider":"qwen","contextLength":262144,"pricing":{"inputPerM":0.21,"outputPerM":1.9},"releasedAt":"2025-09-23","huggingFaceId":"Qwen/Qwen3-VL-235B-A22B-Instruct","profile":{"description":"Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...","inputModalities":["text","image"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":32768,"knowledgeCutoff":"2025-03-31","cacheReadPerM":0.1,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen3","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3-vl-235b-a22b-instruct"}},{"id":"deepseek/deepseek-v3.1-terminus","slug":"deepseek-v3-1-terminus","name":"DeepSeek: DeepSeek V3.1 Terminus","provider":"deepseek","contextLength":163840,"pricing":{"inputPerM":0.27,"outputPerM":1},"releasedAt":"2025-09-22","huggingFaceId":"deepseek-ai/DeepSeek-V3.1-Terminus","profile":{"description":"DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":147456,"knowledgeCutoff":"2025-03-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"DeepSeek","moderated":false,"expiresAt":null,"canonicalSlug":"deepseek/deepseek-v3.1-terminus"}},{"id":"qwen/qwen3-coder-flash","slug":"qwen3-coder-flash","name":"Qwen: Qwen3 Coder Flash","provider":"qwen","contextLength":1000000,"pricing":{"inputPerM":0.195,"outputPerM":0.975},"releasedAt":"2025-09-17","huggingFaceId":null,"profile":{"description":"Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling...","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","tools"],"maxOutput":65536,"knowledgeCutoff":"2025-06-30","cacheReadPerM":0.039,"cacheWritePerM":0.24375,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen3","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3-coder-flash"}},{"id":"qwen/qwen3-next-80b-a3b-thinking","slug":"qwen3-next-80b-a3b-thinking","name":"Qwen: Qwen3 Next 80B A3B Thinking","provider":"qwen","contextLength":262144,"pricing":{"inputPerM":0.15,"outputPerM":1.2},"releasedAt":"2025-09-11","huggingFaceId":"Qwen/Qwen3-Next-80B-A3B-Thinking","profile":{"description":"Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":235929,"knowledgeCutoff":"2025-09-30","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen3","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3-next-80b-a3b-thinking-2509"}},{"id":"qwen/qwen3-next-80b-a3b-instruct","slug":"qwen3-next-80b-a3b-instruct","name":"Qwen: Qwen3 Next 80B A3B Instruct","provider":"qwen","contextLength":262144,"pricing":{"inputPerM":0.09,"outputPerM":1.1},"releasedAt":"2025-09-11","huggingFaceId":"Qwen/Qwen3-Next-80B-A3B-Instruct","profile":{"description":"Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":16384,"knowledgeCutoff":"2025-09-30","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen3","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3-next-80b-a3b-instruct-2509"}},{"id":"moonshotai/kimi-k2-0905","slug":"kimi-k2-0905","name":"MoonshotAI: Kimi K2 0905","provider":"moonshotai","contextLength":262144,"pricing":{"inputPerM":0.6,"outputPerM":2.5},"releasedAt":"2025-09-04","huggingFaceId":"moonshotai/Kimi-K2-Instruct-0905","profile":{"description":"Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":98304,"knowledgeCutoff":"2024-12-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"moonshotai/kimi-k2-0905"}},{"id":"nousresearch/hermes-4-405b","slug":"nousresearch-hermes-4-405b","name":"Nous: Hermes 4 405B","provider":"nousresearch","contextLength":131072,"pricing":{"inputPerM":1,"outputPerM":3},"releasedAt":"2025-08-26","huggingFaceId":"NousResearch/Hermes-4-405B","profile":{"description":"Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs"],"maxOutput":117964,"knowledgeCutoff":"2024-08-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"nousresearch/hermes-4-405b"}},{"id":"deepseek/deepseek-chat-v3.1","slug":"deepseek-chat-v3-1","name":"DeepSeek: DeepSeek V3.1","provider":"deepseek","contextLength":163840,"pricing":{"inputPerM":0.25,"outputPerM":0.95},"releasedAt":"2025-08-21","huggingFaceId":"deepseek-ai/DeepSeek-V3.1","profile":{"description":"DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":32768,"knowledgeCutoff":"2025-03-31","cacheReadPerM":0.13,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"DeepSeek","moderated":false,"expiresAt":null,"canonicalSlug":"deepseek/deepseek-chat-v3.1"}},{"id":"mistralai/mistral-medium-3.1","slug":"mistral-medium-3-1","name":"Mistral: Mistral Medium 3.1","provider":"mistralai","contextLength":131072,"pricing":{"inputPerM":0.4,"outputPerM":2},"releasedAt":"2025-08-13","huggingFaceId":null,"profile":{"description":"Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":104857,"knowledgeCutoff":"2025-06-30","cacheReadPerM":0.04,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Mistral","moderated":false,"expiresAt":null,"canonicalSlug":"mistralai/mistral-medium-3.1"}},{"id":"z-ai/glm-4.5v","slug":"glm-4-5v","name":"Z.ai: GLM 4.5V","provider":"z-ai","contextLength":65536,"pricing":{"inputPerM":0.6,"outputPerM":1.8},"releasedAt":"2025-08-11","huggingFaceId":"zai-org/GLM-4.5V","profile":{"description":"GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding,...","inputModalities":["text","image"],"outputModalities":["text"],"features":["reasoning","json-mode","tools"],"maxOutput":16384,"knowledgeCutoff":"2024-12-31","cacheReadPerM":0.11,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"z-ai/glm-4.5v"}},{"id":"openai/gpt-5","slug":"gpt-5","name":"OpenAI: GPT-5","provider":"openai","contextLength":400000,"pricing":{"inputPerM":1.25,"outputPerM":10},"releasedAt":"2025-08-07","huggingFaceId":null,"profile":{"description":"GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2024-09-30","cacheReadPerM":0.125,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-5-2025-08-07"}},{"id":"openai/gpt-5-mini","slug":"gpt-5-mini","name":"OpenAI: GPT-5 Mini","provider":"openai","contextLength":400000,"pricing":{"inputPerM":0.25,"outputPerM":2},"releasedAt":"2025-08-07","huggingFaceId":null,"profile":{"description":"GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2024-05-31","cacheReadPerM":0.025,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-5-mini-2025-08-07"}},{"id":"openai/gpt-5-nano","slug":"gpt-5-nano","name":"OpenAI: GPT-5 Nano","provider":"openai","contextLength":400000,"pricing":{"inputPerM":0.05,"outputPerM":0.4},"releasedAt":"2025-08-07","huggingFaceId":null,"profile":{"description":"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":128000,"knowledgeCutoff":"2024-05-31","cacheReadPerM":0.005,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-5-nano-2025-08-07"}},{"id":"openai/gpt-oss-120b","slug":"gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"openai","contextLength":131072,"pricing":{"inputPerM":0.15,"outputPerM":0.6},"releasedAt":"2025-08-05","huggingFaceId":"openai/gpt-oss-120b","profile":{"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":65536,"knowledgeCutoff":"2024-06-30","cacheReadPerM":0.075,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"GPT","moderated":false,"expiresAt":null,"canonicalSlug":"openai/gpt-oss-120b"}},{"id":"openai/gpt-oss-20b","slug":"gpt-oss-20b","name":"OpenAI: gpt-oss-20b","provider":"openai","contextLength":131072,"pricing":{"inputPerM":0.018,"outputPerM":0.09},"releasedAt":"2025-08-05","huggingFaceId":"openai/gpt-oss-20b","profile":{"description":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":32768,"knowledgeCutoff":"2024-06-30","cacheReadPerM":0.009,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"GPT","moderated":false,"expiresAt":null,"canonicalSlug":"openai/gpt-oss-20b"}},{"id":"anthropic/claude-opus-4.1","slug":"claude-opus-4-1","name":"Anthropic: Claude Opus 4.1","provider":"anthropic","contextLength":200000,"pricing":{"inputPerM":15,"outputPerM":75},"releasedAt":"2025-08-05","huggingFaceId":null,"profile":{"description":"Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...","inputModalities":["image","text","file"],"outputModalities":["text"],"features":["reasoning","tools"],"maxOutput":32000,"knowledgeCutoff":"2025-01-31","cacheReadPerM":1.5,"cacheWritePerM":18.75,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"Claude","moderated":true,"expiresAt":null,"canonicalSlug":"anthropic/claude-4.1-opus-20250805"}},{"id":"mistralai/codestral-2508","slug":"codestral-2508","name":"Mistral: Codestral 2508","provider":"mistralai","contextLength":256000,"pricing":{"inputPerM":0.3,"outputPerM":0.9},"releasedAt":"2025-08-01","huggingFaceId":null,"profile":{"description":"Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. [Blog Post](https://mistral.ai/news/codestral-25-08)","inputModalities":["text","file"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":204800,"knowledgeCutoff":"2025-03-31","cacheReadPerM":0.03,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Mistral","moderated":false,"expiresAt":null,"canonicalSlug":"mistralai/codestral-2508"}},{"id":"qwen/qwen3-coder-30b-a3b-instruct","slug":"qwen3-coder-30b-a3b-instruct","name":"Qwen: Qwen3 Coder 30B A3B Instruct","provider":"qwen","contextLength":262144,"pricing":{"inputPerM":0.07,"outputPerM":0.28},"releasedAt":"2025-07-31","huggingFaceId":"Qwen/Qwen3-Coder-30B-A3B-Instruct","profile":{"description":"Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":235929,"knowledgeCutoff":"2025-06-30","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen3","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3-coder-30b-a3b-instruct"}},{"id":"qwen/qwen3-30b-a3b-instruct-2507","slug":"qwen3-30b-a3b-instruct-2507","name":"Qwen: Qwen3 30B A3B Instruct 2507","provider":"qwen","contextLength":262144,"pricing":{"inputPerM":0.09,"outputPerM":0.3},"releasedAt":"2025-07-29","huggingFaceId":"Qwen/Qwen3-30B-A3B-Instruct-2507","profile":{"description":"Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":235929,"knowledgeCutoff":"2025-06-30","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen3","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3-30b-a3b-instruct-2507"}},{"id":"z-ai/glm-4.5","slug":"glm-4-5","name":"Z.ai: GLM 4.5","provider":"z-ai","contextLength":131072,"pricing":{"inputPerM":0.6,"outputPerM":2.2},"releasedAt":"2025-07-25","huggingFaceId":"zai-org/GLM-4.5","profile":{"description":"GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","tools"],"maxOutput":98304,"knowledgeCutoff":"2024-12-31","cacheReadPerM":0.11,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":"2026-12-31","canonicalSlug":"z-ai/glm-4.5"}},{"id":"z-ai/glm-4.5-air","slug":"glm-4-5-air","name":"Z.ai: GLM 4.5 Air","provider":"z-ai","contextLength":131072,"pricing":{"inputPerM":0.13,"outputPerM":0.85},"releasedAt":"2025-07-25","huggingFaceId":"zai-org/GLM-4.5-Air","profile":{"description":"GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","tools"],"maxOutput":98304,"knowledgeCutoff":"2024-12-31","cacheReadPerM":0.025,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"z-ai/glm-4.5-air"}},{"id":"qwen/qwen3-235b-a22b-thinking-2507","slug":"qwen3-235b-a22b-thinking-2507","name":"Qwen: Qwen3 235B A22B Thinking 2507","provider":"qwen","contextLength":128000,"pricing":{"inputPerM":0.45,"outputPerM":3.5},"releasedAt":"2025-07-25","huggingFaceId":"Qwen/Qwen3-235B-A22B-Thinking-2507","profile":{"description":"Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","tools"],"maxOutput":16384,"knowledgeCutoff":"2025-06-30","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen3","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3-235b-a22b-thinking-2507"}},{"id":"qwen/qwen3-coder","slug":"qwen3-coder","name":"Qwen: Qwen3 Coder 480B A35B","provider":"qwen","contextLength":262144,"pricing":{"inputPerM":0.3,"outputPerM":1},"releasedAt":"2025-07-23","huggingFaceId":"Qwen/Qwen3-Coder-480B-A35B-Instruct","profile":{"description":"Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":65536,"knowledgeCutoff":"2025-06-30","cacheReadPerM":0.1,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen3","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3-coder-480b-a35b-07-25"}},{"id":"bytedance/ui-tars-1.5-7b","slug":"bytedance-ui-tars-1-5-7b","name":"ByteDance: UI-TARS 7B","provider":"bytedance","contextLength":128000,"pricing":{"inputPerM":0.1,"outputPerM":0.2},"releasedAt":"2025-07-22","huggingFaceId":"ByteDance-Seed/UI-TARS-1.5-7B","profile":{"description":"UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement...","inputModalities":["image","text"],"outputModalities":["text"],"features":["structured-outputs"],"maxOutput":2048,"knowledgeCutoff":"2025-01-31","cacheReadPerM":0.1,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"bytedance/ui-tars-1.5-7b"}},{"id":"google/gemini-2.5-flash-lite","slug":"gemini-2-5-flash-lite","name":"Google: Gemini 2.5 Flash Lite","provider":"google","contextLength":1048576,"pricing":{"inputPerM":0.1,"outputPerM":0.4},"releasedAt":"2025-07-22","huggingFaceId":null,"profile":{"description":"Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...","inputModalities":["text","image","file","audio","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":65535,"knowledgeCutoff":"2025-01-31","cacheReadPerM":0.01,"cacheWritePerM":0.083333,"reasoningPerM":0.4,"webSearchPerRequest":0.014,"tokenizer":"Gemini","moderated":false,"expiresAt":"2026-10-20","canonicalSlug":"google/gemini-2.5-flash-lite"}},{"id":"qwen/qwen3-235b-a22b-2507","slug":"qwen3-235b-a22b-2507","name":"Qwen: Qwen3 235B A22B Instruct 2507","provider":"qwen","contextLength":262144,"pricing":{"inputPerM":0.09,"outputPerM":0.55},"releasedAt":"2025-07-21","huggingFaceId":"Qwen/Qwen3-235B-A22B-Instruct-2507","profile":{"description":"Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":16384,"knowledgeCutoff":"2025-06-30","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen3","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3-235b-a22b-07-25"}},{"id":"moonshotai/kimi-k2","slug":"kimi-k2","name":"MoonshotAI: Kimi K2 0711","provider":"moonshotai","contextLength":131072,"pricing":{"inputPerM":0.57,"outputPerM":2.3},"releasedAt":"2025-07-11","huggingFaceId":"moonshotai/Kimi-K2-Instruct","profile":{"description":"Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...","inputModalities":["text"],"outputModalities":["text"],"features":["tools"],"maxOutput":98304,"knowledgeCutoff":"2024-12-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"moonshotai/kimi-k2"}},{"id":"cognitivecomputations/dolphin-mistral-24b-venice-edition","slug":"cognitivecomputations-dolphin-mistral-24b-venice-edition","name":"Venice: Uncensored","provider":"cognitivecomputations","contextLength":128000,"pricing":{"inputPerM":0.2,"outputPerM":0.9},"releasedAt":"2025-07-09","huggingFaceId":"cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition","profile":{"description":"Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode"],"maxOutput":8192,"knowledgeCutoff":"2024-04-30","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"venice/uncensored"}},{"id":"tencent/hunyuan-a13b-instruct","slug":"tencent-hunyuan-a13b-instruct","name":"Tencent: Hunyuan A13B Instruct","provider":"tencent","contextLength":131072,"pricing":{"inputPerM":0.14,"outputPerM":0.57},"releasedAt":"2025-07-08","huggingFaceId":"tencent/Hunyuan-A13B-Instruct","profile":{"description":"Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs"],"maxOutput":117964,"knowledgeCutoff":"2025-03-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"tencent/hunyuan-a13b-instruct"}},{"id":"morph/morph-v3-large","slug":"morph-morph-v3-large","name":"Morph: Morph V3 Large","provider":"morph","contextLength":262144,"pricing":{"inputPerM":0.9,"outputPerM":1.9},"releasedAt":"2025-07-07","huggingFaceId":null,"profile":{"description":"Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: {instruction} {initial_code}...","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs"],"maxOutput":131072,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"morph/morph-v3-large"}},{"id":"morph/morph-v3-fast","slug":"morph-morph-v3-fast","name":"Morph: Morph V3 Fast","provider":"morph","contextLength":262144,"pricing":{"inputPerM":0.8,"outputPerM":1.2},"releasedAt":"2025-07-07","huggingFaceId":null,"profile":{"description":"Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: {instruction} {initial_code} {edit_snippet}...","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs"],"maxOutput":131072,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"morph/morph-v3-fast"}},{"id":"mistralai/mistral-small-3.2-24b-instruct","slug":"mistral-small-3-2-24b-instruct","name":"Mistral: Mistral Small 3.2 24B","provider":"mistralai","contextLength":256000,"pricing":{"inputPerM":0.09375,"outputPerM":0.25},"releasedAt":"2025-06-20","huggingFaceId":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","profile":{"description":"Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on...","inputModalities":["image","text"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":16384,"knowledgeCutoff":"2023-10-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Mistral","moderated":false,"expiresAt":null,"canonicalSlug":"mistralai/mistral-small-3.2-24b-instruct-2506"}},{"id":"minimax/minimax-m1","slug":"minimax-minimax-m1","name":"MiniMax: MiniMax M1","provider":"minimax","contextLength":1000000,"pricing":{"inputPerM":0.55,"outputPerM":2.2},"releasedAt":"2025-06-17","huggingFaceId":null,"profile":{"description":"MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom \"lightning attention\" mechanism, allowing it...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","tools"],"maxOutput":40000,"knowledgeCutoff":"2024-06-30","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"minimax/minimax-m1"}},{"id":"google/gemini-2.5-flash","slug":"gemini-2-5-flash","name":"Google: Gemini 2.5 Flash","provider":"google","contextLength":1048576,"pricing":{"inputPerM":0.3,"outputPerM":2.5},"releasedAt":"2025-06-17","huggingFaceId":null,"profile":{"description":"Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater...","inputModalities":["file","image","text","audio","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":65535,"knowledgeCutoff":"2025-01-31","cacheReadPerM":0.03,"cacheWritePerM":0.083333,"reasoningPerM":2.5,"webSearchPerRequest":0.014,"tokenizer":"Gemini","moderated":false,"expiresAt":"2026-10-20","canonicalSlug":"google/gemini-2.5-flash"}},{"id":"google/gemini-2.5-pro","slug":"gemini-2-5-pro","name":"Google: Gemini 2.5 Pro","provider":"google","contextLength":1048576,"pricing":{"inputPerM":1.25,"outputPerM":10},"releasedAt":"2025-06-17","huggingFaceId":null,"profile":{"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...","inputModalities":["text","image","file","audio","video"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":65536,"knowledgeCutoff":"2025-01-31","cacheReadPerM":0.125,"cacheWritePerM":0.375,"reasoningPerM":10,"webSearchPerRequest":0.014,"tokenizer":"Gemini","moderated":false,"expiresAt":"2026-10-20","canonicalSlug":"google/gemini-2.5-pro"}},{"id":"openai/o3-pro","slug":"o3-pro","name":"OpenAI: o3 Pro","provider":"openai","contextLength":200000,"pricing":{"inputPerM":20,"outputPerM":80},"releasedAt":"2025-06-10","huggingFaceId":null,"profile":{"description":"The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...","inputModalities":["text","file","image"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":100000,"knowledgeCutoff":"2024-06-30","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/o3-pro-2025-06-10"}},{"id":"google/gemini-2.5-pro-preview","slug":"gemini-2-5-pro-preview","name":"Google: Gemini 2.5 Pro Preview 06-05","provider":"google","contextLength":1048576,"pricing":{"inputPerM":1.25,"outputPerM":10},"releasedAt":"2025-06-05","huggingFaceId":null,"profile":{"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...","inputModalities":["file","image","text","audio"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":65536,"knowledgeCutoff":"2025-01-31","cacheReadPerM":0.125,"cacheWritePerM":0.375,"reasoningPerM":10,"webSearchPerRequest":0.014,"tokenizer":"Gemini","moderated":false,"expiresAt":null,"canonicalSlug":"google/gemini-2.5-pro-preview-06-05"}},{"id":"deepseek/deepseek-r1-0528","slug":"deepseek-r1-0528","name":"DeepSeek: R1 0528","provider":"deepseek","contextLength":163840,"pricing":{"inputPerM":0.5,"outputPerM":2.15},"releasedAt":"2025-05-28","huggingFaceId":"deepseek-ai/DeepSeek-R1-0528","profile":{"description":"May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":32768,"knowledgeCutoff":"2025-03-31","cacheReadPerM":0.35,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"DeepSeek","moderated":false,"expiresAt":null,"canonicalSlug":"deepseek/deepseek-r1-0528"}},{"id":"mistralai/mistral-medium-3","slug":"mistral-medium-3","name":"Mistral: Mistral Medium 3","provider":"mistralai","contextLength":131072,"pricing":{"inputPerM":0.4,"outputPerM":2},"releasedAt":"2025-05-07","huggingFaceId":null,"profile":{"description":"Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":104857,"knowledgeCutoff":"2025-03-31","cacheReadPerM":0.04,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Mistral","moderated":false,"expiresAt":null,"canonicalSlug":"mistralai/mistral-medium-3"}},{"id":"meta-llama/llama-guard-4-12b","slug":"llama-guard-4-12b","name":"Meta: Llama Guard 4 12B","provider":"meta-llama","contextLength":163840,"pricing":{"inputPerM":0.18,"outputPerM":0.18},"releasedAt":"2025-04-30","huggingFaceId":"meta-llama/Llama-Guard-4-12B","profile":{"description":"Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...","inputModalities":["image","text"],"outputModalities":["text"],"features":[],"maxOutput":16384,"knowledgeCutoff":"2024-08-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"meta-llama/llama-guard-4-12b"}},{"id":"qwen/qwen3-30b-a3b","slug":"qwen3-30b-a3b","name":"Qwen: Qwen3 30B A3B","provider":"qwen","contextLength":40960,"pricing":{"inputPerM":0.12,"outputPerM":0.5},"releasedAt":"2025-04-28","huggingFaceId":"Qwen/Qwen3-30B-A3B","profile":{"description":"Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":16384,"knowledgeCutoff":"2025-03-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen3","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3-30b-a3b-04-28"}},{"id":"qwen/qwen3-14b","slug":"qwen3-14b","name":"Qwen: Qwen3 14B","provider":"qwen","contextLength":40960,"pricing":{"inputPerM":0.12,"outputPerM":0.24},"releasedAt":"2025-04-28","huggingFaceId":"Qwen/Qwen3-14B","profile":{"description":"Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":16384,"knowledgeCutoff":"2025-03-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen3","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3-14b-04-28"}},{"id":"qwen/qwen3-32b","slug":"qwen3-32b","name":"Qwen: Qwen3 32B","provider":"qwen","contextLength":131072,"pricing":{"inputPerM":0.08,"outputPerM":0.28},"releasedAt":"2025-04-28","huggingFaceId":"Qwen/Qwen3-32B","profile":{"description":"Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":16384,"knowledgeCutoff":"2025-03-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen3","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen3-32b-04-28"}},{"id":"openai/o4-mini-high","slug":"o4-mini-high","name":"OpenAI: o4 Mini High","provider":"openai","contextLength":200000,"pricing":{"inputPerM":1.1,"outputPerM":4.4},"releasedAt":"2025-04-16","huggingFaceId":null,"profile":{"description":"OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining...","inputModalities":["image","text","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":100000,"knowledgeCutoff":"2024-06-30","cacheReadPerM":0.275,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/o4-mini-high-2025-04-16"}},{"id":"openai/o3","slug":"o3","name":"OpenAI: o3","provider":"openai","contextLength":200000,"pricing":{"inputPerM":2,"outputPerM":8},"releasedAt":"2025-04-16","huggingFaceId":null,"profile":{"description":"o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....","inputModalities":["image","text","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":100000,"knowledgeCutoff":"2024-06-30","cacheReadPerM":0.5,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/o3-2025-04-16"}},{"id":"openai/o4-mini","slug":"o4-mini","name":"OpenAI: o4 Mini","provider":"openai","contextLength":200000,"pricing":{"inputPerM":1.1,"outputPerM":4.4},"releasedAt":"2025-04-16","huggingFaceId":null,"profile":{"description":"OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...","inputModalities":["image","text","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":100000,"knowledgeCutoff":"2024-06-30","cacheReadPerM":0.275,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/o4-mini-2025-04-16"}},{"id":"openai/gpt-4.1","slug":"gpt-4-1","name":"OpenAI: GPT-4.1","provider":"openai","contextLength":1047576,"pricing":{"inputPerM":2,"outputPerM":8},"releasedAt":"2025-04-14","huggingFaceId":null,"profile":{"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...","inputModalities":["image","text","file"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":32768,"knowledgeCutoff":"2024-06-30","cacheReadPerM":0.5,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-4.1-2025-04-14"}},{"id":"openai/gpt-4.1-mini","slug":"gpt-4-1-mini","name":"OpenAI: GPT-4.1 Mini","provider":"openai","contextLength":1047576,"pricing":{"inputPerM":0.4,"outputPerM":1.6},"releasedAt":"2025-04-14","huggingFaceId":null,"profile":{"description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...","inputModalities":["image","text","file"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":32768,"knowledgeCutoff":"2024-06-30","cacheReadPerM":0.1,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-4.1-mini-2025-04-14"}},{"id":"openai/gpt-4.1-nano","slug":"gpt-4-1-nano","name":"OpenAI: GPT-4.1 Nano","provider":"openai","contextLength":1047576,"pricing":{"inputPerM":0.1,"outputPerM":0.4},"releasedAt":"2025-04-14","huggingFaceId":null,"profile":{"description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...","inputModalities":["image","text","file"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":32768,"knowledgeCutoff":"2024-06-30","cacheReadPerM":0.025,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-4.1-nano-2025-04-14"}},{"id":"meta-llama/llama-4-maverick","slug":"llama-4-maverick","name":"Meta: Llama 4 Maverick","provider":"meta-llama","contextLength":524288,"pricing":{"inputPerM":0.1875,"outputPerM":0.6525},"releasedAt":"2025-04-05","huggingFaceId":"meta-llama/Llama-4-Maverick-17B-128E-Instruct","profile":{"description":"Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...","inputModalities":["text","image"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":16384,"knowledgeCutoff":"2024-08-31","cacheReadPerM":0.05,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Llama4","moderated":false,"expiresAt":null,"canonicalSlug":"meta-llama/llama-4-maverick-17b-128e-instruct"}},{"id":"meta-llama/llama-4-scout","slug":"llama-4-scout","name":"Meta: Llama 4 Scout","provider":"meta-llama","contextLength":1310720,"pricing":{"inputPerM":0.1,"outputPerM":0.3},"releasedAt":"2025-04-05","huggingFaceId":"meta-llama/Llama-4-Scout-17B-16E-Instruct","profile":{"description":"Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...","inputModalities":["text","image"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":16384,"knowledgeCutoff":"2024-08-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Llama4","moderated":false,"expiresAt":null,"canonicalSlug":"meta-llama/llama-4-scout-17b-16e-instruct"}},{"id":"deepseek/deepseek-chat-v3-0324","slug":"deepseek-chat-v3-0324","name":"DeepSeek: DeepSeek V3 0324","provider":"deepseek","contextLength":163840,"pricing":{"inputPerM":0.29,"outputPerM":1.14},"releasedAt":"2025-03-24","huggingFaceId":"deepseek-ai/DeepSeek-V3-0324","profile":{"description":"DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":115200,"knowledgeCutoff":"2024-07-31","cacheReadPerM":0.11,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"DeepSeek","moderated":false,"expiresAt":null,"canonicalSlug":"deepseek/deepseek-chat-v3-0324"}},{"id":"openai/o1-pro","slug":"o1-pro","name":"OpenAI: o1-pro","provider":"openai","contextLength":200000,"pricing":{"inputPerM":150,"outputPerM":600},"releasedAt":"2025-03-19","huggingFaceId":null,"profile":{"description":"The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs"],"maxOutput":100000,"knowledgeCutoff":"2023-10-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/o1-pro"}},{"id":"mistralai/mistral-small-3.1-24b-instruct","slug":"mistral-small-3-1-24b-instruct","name":"Mistral: Mistral Small 3.1 24B","provider":"mistralai","contextLength":128000,"pricing":{"inputPerM":0.351,"outputPerM":0.555},"releasedAt":"2025-03-17","huggingFaceId":"mistralai/Mistral-Small-3.1-24B-Instruct-2503","profile":{"description":"Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and...","inputModalities":["text","image"],"outputModalities":["text"],"features":["structured-outputs","tools"],"maxOutput":102400,"knowledgeCutoff":"2023-10-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Mistral","moderated":false,"expiresAt":null,"canonicalSlug":"mistralai/mistral-small-3.1-24b-instruct-2503"}},{"id":"google/gemma-3-4b-it","slug":"gemma-3-4b-it","name":"Google: Gemma 3 4B","provider":"google","contextLength":131072,"pricing":{"inputPerM":0.04,"outputPerM":0.05},"releasedAt":"2025-03-13","huggingFaceId":"google/gemma-3-4b-it","profile":{"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...","inputModalities":["text","image"],"outputModalities":["text"],"features":["json-mode","structured-outputs"],"maxOutput":117964,"knowledgeCutoff":"2024-08-31","cacheReadPerM":0.02,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Gemini","moderated":false,"expiresAt":null,"canonicalSlug":"google/gemma-3-4b-it"}},{"id":"google/gemma-3-12b-it","slug":"gemma-3-12b-it","name":"Google: Gemma 3 12B","provider":"google","contextLength":131072,"pricing":{"inputPerM":0.05,"outputPerM":0.15},"releasedAt":"2025-03-13","huggingFaceId":"google/gemma-3-12b-it","profile":{"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...","inputModalities":["text","image"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":16384,"knowledgeCutoff":"2024-08-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Gemini","moderated":false,"expiresAt":null,"canonicalSlug":"google/gemma-3-12b-it"}},{"id":"cohere/command-a","slug":"cohere-command-a","name":"Cohere: Command A","provider":"cohere","contextLength":256000,"pricing":{"inputPerM":2.5,"outputPerM":10},"releasedAt":"2025-03-13","huggingFaceId":"CohereForAI/c4ai-command-a-03-2025","profile":{"description":"Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs"],"maxOutput":8192,"knowledgeCutoff":"2024-08-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":true,"expiresAt":null,"canonicalSlug":"cohere/command-a-03-2025"}},{"id":"rekaai/reka-flash-3","slug":"rekaai-reka-flash-3","name":"Reka Flash 3","provider":"rekaai","contextLength":65536,"pricing":{"inputPerM":0.1,"outputPerM":0.2},"releasedAt":"2025-03-12","huggingFaceId":"RekaAI/reka-flash-3","profile":{"description":"Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","structured-outputs"],"maxOutput":58982,"knowledgeCutoff":"2025-01-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"rekaai/reka-flash-3"}},{"id":"google/gemma-3-27b-it","slug":"gemma-3-27b-it","name":"Google: Gemma 3 27B","provider":"google","contextLength":131072,"pricing":{"inputPerM":0.08,"outputPerM":0.35},"releasedAt":"2025-03-12","huggingFaceId":"google/gemma-3-27b-it","profile":{"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...","inputModalities":["text","image"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":117964,"knowledgeCutoff":"2024-08-31","cacheReadPerM":0.04,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Gemini","moderated":false,"expiresAt":null,"canonicalSlug":"google/gemma-3-27b-it"}},{"id":"thedrummer/skyfall-36b-v2","slug":"thedrummer-skyfall-36b-v2","name":"TheDrummer: Skyfall 36B V2","provider":"thedrummer","contextLength":32768,"pricing":{"inputPerM":0.55,"outputPerM":0.8},"releasedAt":"2025-03-10","huggingFaceId":"TheDrummer/Skyfall-36B-v2","profile":{"description":"Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs"],"maxOutput":29491,"knowledgeCutoff":"2024-06-30","cacheReadPerM":0.25,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"thedrummer/skyfall-36b-v2"}},{"id":"perplexity/sonar-reasoning-pro","slug":"perplexity-sonar-reasoning-pro","name":"Perplexity: Sonar Reasoning Pro","provider":"perplexity","contextLength":128000,"pricing":{"inputPerM":2,"outputPerM":8},"releasedAt":"2025-03-07","huggingFaceId":null,"profile":{"description":"Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for...","inputModalities":["text","image"],"outputModalities":["text"],"features":["reasoning","web-search"],"maxOutput":115200,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.005,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"perplexity/sonar-reasoning-pro"}},{"id":"perplexity/sonar-pro","slug":"perplexity-sonar-pro","name":"Perplexity: Sonar Pro","provider":"perplexity","contextLength":200000,"pricing":{"inputPerM":3,"outputPerM":15},"releasedAt":"2025-03-07","huggingFaceId":null,"profile":{"description":"Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like...","inputModalities":["text","image"],"outputModalities":["text"],"features":["web-search"],"maxOutput":8000,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.005,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"perplexity/sonar-pro"}},{"id":"perplexity/sonar-deep-research","slug":"perplexity-sonar-deep-research","name":"Perplexity: Sonar Deep Research","provider":"perplexity","contextLength":128000,"pricing":{"inputPerM":2,"outputPerM":8},"releasedAt":"2025-03-07","huggingFaceId":null,"profile":{"description":"Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...","inputModalities":["text"],"outputModalities":["text"],"features":["reasoning","web-search"],"maxOutput":115200,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":3,"webSearchPerRequest":0.005,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"perplexity/sonar-deep-research"}},{"id":"mistralai/mistral-saba","slug":"mistral-saba","name":"Mistral: Saba","provider":"mistralai","contextLength":32768,"pricing":{"inputPerM":0.2,"outputPerM":0.6},"releasedAt":"2025-02-17","huggingFaceId":null,"profile":{"description":"Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional...","inputModalities":["text","file"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":26214,"knowledgeCutoff":"2024-09-30","cacheReadPerM":0.02,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Mistral","moderated":false,"expiresAt":null,"canonicalSlug":"mistralai/mistral-saba-2502"}},{"id":"openai/o3-mini-high","slug":"o3-mini-high","name":"OpenAI: o3 Mini High","provider":"openai","contextLength":200000,"pricing":{"inputPerM":1.1,"outputPerM":4.4},"releasedAt":"2025-02-12","huggingFaceId":null,"profile":{"description":"OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and...","inputModalities":["text","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":100000,"knowledgeCutoff":"2023-10-31","cacheReadPerM":0.55,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/o3-mini-high-2025-01-31"}},{"id":"aion-labs/aion-rp-llama-3.1-8b","slug":"aion-labs-aion-rp-llama-3-1-8b","name":"AionLabs: Aion-RP 1.0 (8B)","provider":"aion-labs","contextLength":32768,"pricing":{"inputPerM":0.8,"outputPerM":1.6},"releasedAt":"2025-02-04","huggingFaceId":null,"profile":{"description":"Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model...","inputModalities":["text"],"outputModalities":["text"],"features":[],"maxOutput":29491,"knowledgeCutoff":"2023-12-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"aion-labs/aion-rp-llama-3.1-8b"}},{"id":"qwen/qwen2.5-vl-72b-instruct","slug":"qwen2-5-vl-72b-instruct","name":"Qwen: Qwen2.5 VL 72B Instruct","provider":"qwen","contextLength":128000,"pricing":{"inputPerM":0.8,"outputPerM":1},"releasedAt":"2025-02-01","huggingFaceId":"Qwen/Qwen2.5-VL-72B-Instruct","profile":{"description":"Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.","inputModalities":["text","image"],"outputModalities":["text"],"features":["json-mode","structured-outputs"],"maxOutput":115200,"knowledgeCutoff":"2024-06-30","cacheReadPerM":0.4,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen2.5-vl-72b-instruct"}},{"id":"qwen/qwen-plus","slug":"qwen-plus","name":"Qwen: Qwen-Plus","provider":"qwen","contextLength":1000000,"pricing":{"inputPerM":0.26,"outputPerM":0.78},"releasedAt":"2025-02-01","huggingFaceId":null,"profile":{"description":"Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":32768,"knowledgeCutoff":"2025-03-31","cacheReadPerM":0.052,"cacheWritePerM":0.325,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen-plus-2025-01-25"}},{"id":"openai/o3-mini","slug":"o3-mini","name":"OpenAI: o3 Mini","provider":"openai","contextLength":200000,"pricing":{"inputPerM":1.1,"outputPerM":4.4},"releasedAt":"2025-01-31","huggingFaceId":null,"profile":{"description":"OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to...","inputModalities":["text","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":100000,"knowledgeCutoff":"2023-10-31","cacheReadPerM":0.55,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/o3-mini-2025-01-31"}},{"id":"mistralai/mistral-small-24b-instruct-2501","slug":"mistral-small-24b-instruct-2501","name":"Mistral: Mistral Small 3","provider":"mistralai","contextLength":32768,"pricing":{"inputPerM":0.05,"outputPerM":0.08},"releasedAt":"2025-01-30","huggingFaceId":"mistralai/Mistral-Small-24B-Instruct-2501","profile":{"description":"Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs"],"maxOutput":16384,"knowledgeCutoff":"2023-10-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Mistral","moderated":false,"expiresAt":null,"canonicalSlug":"mistralai/mistral-small-24b-instruct-2501"}},{"id":"perplexity/sonar","slug":"perplexity-sonar","name":"Perplexity: Sonar","provider":"perplexity","contextLength":127072,"pricing":{"inputPerM":1,"outputPerM":1},"releasedAt":"2025-01-27","huggingFaceId":null,"profile":{"description":"Sonar is lightweight, affordable, fast, and simple to use, now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features...","inputModalities":["text","image"],"outputModalities":["text"],"features":["web-search"],"maxOutput":114364,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.005,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"perplexity/sonar"}},{"id":"minimax/minimax-01","slug":"minimax-minimax-01","name":"MiniMax: MiniMax-01","provider":"minimax","contextLength":1000192,"pricing":{"inputPerM":0.2,"outputPerM":1.1},"releasedAt":"2025-01-15","huggingFaceId":"MiniMaxAI/MiniMax-Text-01","profile":{"description":"MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context...","inputModalities":["text","image"],"outputModalities":["text"],"features":[],"maxOutput":900172,"knowledgeCutoff":"2024-03-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"minimax/minimax-01"}},{"id":"microsoft/phi-4","slug":"microsoft-phi-4","name":"Microsoft: Phi 4","provider":"microsoft","contextLength":16384,"pricing":{"inputPerM":0.07,"outputPerM":0.14},"releasedAt":"2025-01-10","huggingFaceId":"microsoft/phi-4","profile":{"description":"[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs"],"maxOutput":14745,"knowledgeCutoff":"2024-06-30","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":null,"moderated":false,"expiresAt":null,"canonicalSlug":"microsoft/phi-4"}},{"id":"deepseek/deepseek-chat","slug":"deepseek-chat","name":"DeepSeek: DeepSeek V3","provider":"deepseek","contextLength":163840,"pricing":{"inputPerM":0.2574,"outputPerM":1.0287},"releasedAt":"2024-12-26","huggingFaceId":"deepseek-ai/DeepSeek-V3","profile":{"description":"DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":16000,"knowledgeCutoff":"2024-07-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"DeepSeek","moderated":false,"expiresAt":null,"canonicalSlug":"deepseek/deepseek-chat-v3"}},{"id":"openai/o1","slug":"o1","name":"OpenAI: o1","provider":"openai","contextLength":200000,"pricing":{"inputPerM":15,"outputPerM":60},"releasedAt":"2024-12-17","huggingFaceId":null,"profile":{"description":"The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["reasoning","json-mode","structured-outputs","tools"],"maxOutput":100000,"knowledgeCutoff":"2023-10-31","cacheReadPerM":7.5,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":0.01,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/o1-2024-12-17"}},{"id":"cohere/command-r7b-12-2024","slug":"cohere-command-r7b-12-2024","name":"Cohere: Command R7B (12-2024)","provider":"cohere","contextLength":128000,"pricing":{"inputPerM":0.0375,"outputPerM":0.15},"releasedAt":"2024-12-14","huggingFaceId":null,"profile":{"description":"Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning...","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs"],"maxOutput":4000,"knowledgeCutoff":"2024-08-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Cohere","moderated":true,"expiresAt":null,"canonicalSlug":"cohere/command-r7b-12-2024"}},{"id":"meta-llama/llama-3.3-70b-instruct","slug":"llama-3-3-70b-instruct","name":"Meta: Llama 3.3 70B Instruct","provider":"meta-llama","contextLength":131072,"pricing":{"inputPerM":0.1,"outputPerM":0.32},"releasedAt":"2024-12-06","huggingFaceId":"meta-llama/Llama-3.3-70B-Instruct","profile":{"description":"The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":16384,"knowledgeCutoff":"2023-12-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Llama3","moderated":false,"expiresAt":null,"canonicalSlug":"meta-llama/llama-3.3-70b-instruct"}},{"id":"amazon/nova-lite-v1","slug":"amazon-nova-lite-v1","name":"Amazon: Nova Lite 1.0","provider":"amazon","contextLength":300000,"pricing":{"inputPerM":0.06,"outputPerM":0.24},"releasedAt":"2024-12-05","huggingFaceId":null,"profile":{"description":"Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite...","inputModalities":["text","image"],"outputModalities":["text"],"features":["tools"],"maxOutput":5120,"knowledgeCutoff":"2024-10-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Nova","moderated":true,"expiresAt":null,"canonicalSlug":"amazon/nova-lite-v1"}},{"id":"amazon/nova-micro-v1","slug":"amazon-nova-micro-v1","name":"Amazon: Nova Micro 1.0","provider":"amazon","contextLength":128000,"pricing":{"inputPerM":0.035,"outputPerM":0.14},"releasedAt":"2024-12-05","huggingFaceId":null,"profile":{"description":"Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length...","inputModalities":["text"],"outputModalities":["text"],"features":["tools"],"maxOutput":5120,"knowledgeCutoff":"2024-10-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Nova","moderated":true,"expiresAt":null,"canonicalSlug":"amazon/nova-micro-v1"}},{"id":"amazon/nova-pro-v1","slug":"amazon-nova-pro-v1","name":"Amazon: Nova Pro 1.0","provider":"amazon","contextLength":300000,"pricing":{"inputPerM":0.8,"outputPerM":3.2},"releasedAt":"2024-12-05","huggingFaceId":null,"profile":{"description":"Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December...","inputModalities":["text","image"],"outputModalities":["text"],"features":["tools"],"maxOutput":5120,"knowledgeCutoff":"2024-10-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Nova","moderated":true,"expiresAt":null,"canonicalSlug":"amazon/nova-pro-v1"}},{"id":"openai/gpt-4o-2024-11-20","slug":"gpt-4o-2024-11-20","name":"OpenAI: GPT-4o (2024-11-20)","provider":"openai","contextLength":128000,"pricing":{"inputPerM":2.5,"outputPerM":10},"releasedAt":"2024-11-20","huggingFaceId":null,"profile":{"description":"The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools","web-search"],"maxOutput":16384,"knowledgeCutoff":"2023-10-31","cacheReadPerM":1.25,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-4o-2024-11-20"}},{"id":"mistralai/mistral-large-2407","slug":"mistral-large-2407","name":"Mistral Large 2407","provider":"mistralai","contextLength":131072,"pricing":{"inputPerM":2,"outputPerM":6},"releasedAt":"2024-11-19","huggingFaceId":null,"profile":{"description":"This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....","inputModalities":["text","file"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":104857,"knowledgeCutoff":"2024-03-31","cacheReadPerM":0.2,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Mistral","moderated":false,"expiresAt":null,"canonicalSlug":"mistralai/mistral-large-2407"}},{"id":"qwen/qwen-2.5-coder-32b-instruct","slug":"qwen-2-5-coder-32b-instruct","name":"Qwen2.5 Coder 32B Instruct","provider":"qwen","contextLength":32768,"pricing":{"inputPerM":0.66,"outputPerM":1},"releasedAt":"2024-11-11","huggingFaceId":"Qwen/Qwen2.5-Coder-32B-Instruct","profile":{"description":"Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in **code generation**, **code reasoning**...","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode"],"maxOutput":29491,"knowledgeCutoff":"2024-06-30","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen-2.5-coder-32b-instruct"}},{"id":"thedrummer/unslopnemo-12b","slug":"thedrummer-unslopnemo-12b","name":"TheDrummer: UnslopNemo 12B","provider":"thedrummer","contextLength":1024000,"pricing":{"inputPerM":0.4,"outputPerM":0.4},"releasedAt":"2024-11-08","huggingFaceId":"TheDrummer/UnslopNemo-12B-v4.1","profile":{"description":"UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios.","inputModalities":["text"],"outputModalities":["text"],"features":["structured-outputs"],"maxOutput":819200,"knowledgeCutoff":"2024-04-30","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Mistral","moderated":false,"expiresAt":null,"canonicalSlug":"thedrummer/unslopnemo-12b"}},{"id":"anthracite-org/magnum-v4-72b","slug":"anthracite-org-magnum-v4-72b","name":"Magnum v4 72B","provider":"anthracite-org","contextLength":32768,"pricing":{"inputPerM":2.5,"outputPerM":5},"releasedAt":"2024-10-22","huggingFaceId":"anthracite-org/magnum-v4-72b","profile":{"description":"This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus). The model is fine-tuned on top of [Qwen2.5 72B](https://openrouter.ai/qwen/qwen-2.5-72b-instruct).","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs"],"maxOutput":4096,"knowledgeCutoff":"2024-06-30","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen","moderated":false,"expiresAt":null,"canonicalSlug":"anthracite-org/magnum-v4-72b"}},{"id":"qwen/qwen-2.5-7b-instruct","slug":"qwen-2-5-7b-instruct","name":"Qwen: Qwen2.5 7B Instruct","provider":"qwen","contextLength":32768,"pricing":{"inputPerM":0.1,"outputPerM":0.2},"releasedAt":"2024-10-16","huggingFaceId":"Qwen/Qwen2.5-7B-Instruct","profile":{"description":"Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":29491,"knowledgeCutoff":"2024-06-30","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen-2.5-7b-instruct"}},{"id":"meta-llama/llama-3.2-1b-instruct","slug":"llama-3-2-1b-instruct","name":"Meta: Llama 3.2 1B Instruct","provider":"meta-llama","contextLength":60000,"pricing":{"inputPerM":0.027,"outputPerM":0.201},"releasedAt":"2024-09-25","huggingFaceId":"meta-llama/Llama-3.2-1B-Instruct","profile":{"description":"Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate...","inputModalities":["text"],"outputModalities":["text"],"features":[],"maxOutput":54000,"knowledgeCutoff":"2023-12-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Llama3","moderated":false,"expiresAt":null,"canonicalSlug":"meta-llama/llama-3.2-1b-instruct"}},{"id":"meta-llama/llama-3.2-3b-instruct","slug":"llama-3-2-3b-instruct","name":"Meta: Llama 3.2 3B Instruct","provider":"meta-llama","contextLength":131072,"pricing":{"inputPerM":0.0509,"outputPerM":0.335},"releasedAt":"2024-09-25","huggingFaceId":"meta-llama/Llama-3.2-3B-Instruct","profile":{"description":"Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...","inputModalities":["text"],"outputModalities":["text"],"features":["structured-outputs"],"maxOutput":72000,"knowledgeCutoff":"2023-12-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Llama3","moderated":false,"expiresAt":null,"canonicalSlug":"meta-llama/llama-3.2-3b-instruct"}},{"id":"qwen/qwen-2.5-72b-instruct","slug":"qwen-2-5-72b-instruct","name":"Qwen2.5 72B Instruct","provider":"qwen","contextLength":32768,"pricing":{"inputPerM":0.36,"outputPerM":0.4},"releasedAt":"2024-09-19","huggingFaceId":"Qwen/Qwen2.5-72B-Instruct","profile":{"description":"Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":16384,"knowledgeCutoff":"2024-06-30","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Qwen","moderated":false,"expiresAt":null,"canonicalSlug":"qwen/qwen-2.5-72b-instruct"}},{"id":"cohere/command-r-08-2024","slug":"cohere-command-r-08-2024","name":"Cohere: Command R (08-2024)","provider":"cohere","contextLength":128000,"pricing":{"inputPerM":0.15,"outputPerM":0.6},"releasedAt":"2024-08-30","huggingFaceId":null,"profile":{"description":"command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and...","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":4000,"knowledgeCutoff":"2024-03-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Cohere","moderated":true,"expiresAt":null,"canonicalSlug":"cohere/command-r-08-2024"}},{"id":"cohere/command-r-plus-08-2024","slug":"cohere-command-r-plus-08-2024","name":"Cohere: Command R+ (08-2024)","provider":"cohere","contextLength":128000,"pricing":{"inputPerM":2.5,"outputPerM":10},"releasedAt":"2024-08-30","huggingFaceId":null,"profile":{"description":"command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint...","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":4000,"knowledgeCutoff":"2024-03-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Cohere","moderated":true,"expiresAt":null,"canonicalSlug":"cohere/command-r-plus-08-2024"}},{"id":"sao10k/l3.1-euryale-70b","slug":"sao10k-l3-1-euryale-70b","name":"Sao10K: Llama 3.1 Euryale 70B v2.2","provider":"sao10k","contextLength":131072,"pricing":{"inputPerM":0.85,"outputPerM":0.85},"releasedAt":"2024-08-28","huggingFaceId":"Sao10K/L3.1-70B-Euryale-v2.2","profile":{"description":"Euryale L3.1 70B v2.2 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.1](/models/sao10k/l3-euryale-70b).","inputModalities":["text"],"outputModalities":["text"],"features":["structured-outputs"],"maxOutput":16384,"knowledgeCutoff":"2023-12-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Llama3","moderated":false,"expiresAt":null,"canonicalSlug":"sao10k/l3.1-euryale-70b"}},{"id":"nousresearch/hermes-3-llama-3.1-70b","slug":"nousresearch-hermes-3-llama-3-1-70b","name":"Nous: Hermes 3 70B Instruct","provider":"nousresearch","contextLength":131072,"pricing":{"inputPerM":0.7,"outputPerM":0.7},"releasedAt":"2024-08-18","huggingFaceId":"NousResearch/Hermes-3-Llama-3.1-70B","profile":{"description":"Hermes 3 is a generalist language model with many improvements over [Hermes 2](/models/nousresearch/nous-hermes-2-mistral-7b-dpo), including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...","inputModalities":["text"],"outputModalities":["text"],"features":["structured-outputs"],"maxOutput":16384,"knowledgeCutoff":"2023-12-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Llama3","moderated":false,"expiresAt":"2026-11-02","canonicalSlug":"nousresearch/hermes-3-llama-3.1-70b"}},{"id":"nousresearch/hermes-3-llama-3.1-405b","slug":"nousresearch-hermes-3-llama-3-1-405b","name":"Nous: Hermes 3 405B Instruct","provider":"nousresearch","contextLength":131072,"pricing":{"inputPerM":1,"outputPerM":1},"releasedAt":"2024-08-16","huggingFaceId":"NousResearch/Hermes-3-Llama-3.1-405B","profile":{"description":"Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs"],"maxOutput":16384,"knowledgeCutoff":"2023-12-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Llama3","moderated":false,"expiresAt":"2026-11-02","canonicalSlug":"nousresearch/hermes-3-llama-3.1-405b"}},{"id":"sao10k/l3-lunaris-8b","slug":"sao10k-l3-lunaris-8b","name":"Sao10K: Llama 3 8B Lunaris","provider":"sao10k","contextLength":8192,"pricing":{"inputPerM":0.04,"outputPerM":0.05},"releasedAt":"2024-08-13","huggingFaceId":"Sao10K/L3-8B-Lunaris-v1","profile":{"description":"Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge....","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs"],"maxOutput":7372,"knowledgeCutoff":"2023-12-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Llama3","moderated":false,"expiresAt":null,"canonicalSlug":"sao10k/l3-lunaris-8b"}},{"id":"openai/gpt-4o-2024-08-06","slug":"gpt-4o-2024-08-06","name":"OpenAI: GPT-4o (2024-08-06)","provider":"openai","contextLength":128000,"pricing":{"inputPerM":2.5,"outputPerM":10},"releasedAt":"2024-08-06","huggingFaceId":null,"profile":{"description":"The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs-in-the-api/). GPT-4o (\"o\" for \"omni\") is...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools","web-search"],"maxOutput":16384,"knowledgeCutoff":"2023-10-31","cacheReadPerM":1.25,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-4o-2024-08-06"}},{"id":"meta-llama/llama-3.1-70b-instruct","slug":"llama-3-1-70b-instruct","name":"Meta: Llama 3.1 70B Instruct","provider":"meta-llama","contextLength":131072,"pricing":{"inputPerM":0.4,"outputPerM":0.4},"releasedAt":"2024-07-23","huggingFaceId":"meta-llama/Meta-Llama-3.1-70B-Instruct","profile":{"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong...","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":16384,"knowledgeCutoff":"2023-12-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Llama3","moderated":false,"expiresAt":null,"canonicalSlug":"meta-llama/llama-3.1-70b-instruct"}},{"id":"meta-llama/llama-3.1-8b-instruct","slug":"llama-3-1-8b-instruct","name":"Meta: Llama 3.1 8B Instruct","provider":"meta-llama","contextLength":131072,"pricing":{"inputPerM":0.05,"outputPerM":0.08},"releasedAt":"2024-07-23","huggingFaceId":"meta-llama/Meta-Llama-3.1-8B-Instruct","profile":{"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":117964,"knowledgeCutoff":"2023-12-31","cacheReadPerM":0.025,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Llama3","moderated":false,"expiresAt":null,"canonicalSlug":"meta-llama/llama-3.1-8b-instruct"}},{"id":"mistralai/mistral-nemo","slug":"mistral-nemo","name":"Mistral: Mistral Nemo","provider":"mistralai","contextLength":131072,"pricing":{"inputPerM":0.029,"outputPerM":0.03},"releasedAt":"2024-07-19","huggingFaceId":"mistralai/Mistral-Nemo-Instruct-2407","profile":{"description":"A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":16384,"knowledgeCutoff":"2024-04-30","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Mistral","moderated":false,"expiresAt":null,"canonicalSlug":"mistralai/mistral-nemo"}},{"id":"openai/gpt-4o-mini","slug":"gpt-4o-mini","name":"OpenAI: GPT-4o-mini","provider":"openai","contextLength":128000,"pricing":{"inputPerM":0.15,"outputPerM":0.6},"releasedAt":"2024-07-18","huggingFaceId":null,"profile":{"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools","web-search"],"maxOutput":16384,"knowledgeCutoff":"2023-10-31","cacheReadPerM":0.075,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-4o-mini"}},{"id":"openai/gpt-4o-mini-2024-07-18","slug":"gpt-4o-mini-2024-07-18","name":"OpenAI: GPT-4o-mini (2024-07-18)","provider":"openai","contextLength":128000,"pricing":{"inputPerM":0.15,"outputPerM":0.6},"releasedAt":"2024-07-18","huggingFaceId":null,"profile":{"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools","web-search"],"maxOutput":16384,"knowledgeCutoff":"2023-10-31","cacheReadPerM":0.075,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-4o-mini-2024-07-18"}},{"id":"google/gemma-2-27b-it","slug":"gemma-2-27b-it","name":"Google: Gemma 2 27B","provider":"google","contextLength":8192,"pricing":{"inputPerM":0.65,"outputPerM":0.65},"releasedAt":"2024-07-13","huggingFaceId":"google/gemma-2-27b-it","profile":{"description":"Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of...","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs"],"maxOutput":2048,"knowledgeCutoff":"2024-06-30","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Gemini","moderated":false,"expiresAt":null,"canonicalSlug":"google/gemma-2-27b-it"}},{"id":"openai/gpt-4o","slug":"gpt-4o","name":"OpenAI: GPT-4o","provider":"openai","contextLength":128000,"pricing":{"inputPerM":2.5,"outputPerM":10},"releasedAt":"2024-05-13","huggingFaceId":null,"profile":{"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools","web-search"],"maxOutput":16384,"knowledgeCutoff":"2023-10-31","cacheReadPerM":1.25,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-4o"}},{"id":"openai/gpt-4o-2024-05-13","slug":"gpt-4o-2024-05-13","name":"OpenAI: GPT-4o (2024-05-13)","provider":"openai","contextLength":128000,"pricing":{"inputPerM":5,"outputPerM":15},"releasedAt":"2024-05-13","huggingFaceId":null,"profile":{"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...","inputModalities":["text","image","file"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools","web-search"],"maxOutput":4096,"knowledgeCutoff":"2023-10-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"GPT","moderated":false,"expiresAt":null,"canonicalSlug":"openai/gpt-4o-2024-05-13"}},{"id":"mistralai/mixtral-8x22b-instruct","slug":"mixtral-8x22b-instruct","name":"Mistral: Mixtral 8x22B Instruct","provider":"mistralai","contextLength":65536,"pricing":{"inputPerM":2,"outputPerM":6},"releasedAt":"2024-04-17","huggingFaceId":"mistralai/Mixtral-8x22B-Instruct-v0.1","profile":{"description":"Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...","inputModalities":["text","file"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":52428,"knowledgeCutoff":"2024-01-31","cacheReadPerM":0.2,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Mistral","moderated":false,"expiresAt":null,"canonicalSlug":"mistralai/mixtral-8x22b-instruct"}},{"id":"openai/gpt-4-turbo","slug":"gpt-4-turbo","name":"OpenAI: GPT-4 Turbo","provider":"openai","contextLength":128000,"pricing":{"inputPerM":10,"outputPerM":30},"releasedAt":"2024-04-09","huggingFaceId":null,"profile":{"description":"The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to December 2023.","inputModalities":["text","image"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":4096,"knowledgeCutoff":"2023-12-31","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-4-turbo"}},{"id":"mistralai/mistral-large","slug":"mistral-large","name":"Mistral Large","provider":"mistralai","contextLength":128000,"pricing":{"inputPerM":2,"outputPerM":6},"releasedAt":"2024-02-26","huggingFaceId":null,"profile":{"description":"This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....","inputModalities":["text","file"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":102400,"knowledgeCutoff":"2024-11-30","cacheReadPerM":0.2,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Mistral","moderated":false,"expiresAt":null,"canonicalSlug":"mistralai/mistral-large"}},{"id":"openai/gpt-3.5-turbo-0613","slug":"gpt-3-5-turbo-0613","name":"OpenAI: GPT-3.5 Turbo (older v0613)","provider":"openai","contextLength":4095,"pricing":{"inputPerM":1,"outputPerM":2},"releasedAt":"2024-01-25","huggingFaceId":null,"profile":{"description":"GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021.","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":3685,"knowledgeCutoff":"2021-09-30","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"GPT","moderated":false,"expiresAt":null,"canonicalSlug":"openai/gpt-3.5-turbo-0613"}},{"id":"openrouter/auto","slug":"openrouter-auto","name":"Auto Router","provider":"openrouter","contextLength":2000000,"pricing":null,"releasedAt":"2023-11-08","huggingFaceId":null,"profile":{"description":"The Auto Router automatically selects the best model for your prompt, powered by the wisdom of the market. It routes you based on what the OpenRouter community collectively spends on...","inputModalities":["text","image","audio","file","video"],"outputModalities":["text","image"],"features":["reasoning","json-mode","structured-outputs","tools","web-search"],"maxOutput":null,"knowledgeCutoff":null,"cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Router","moderated":false,"expiresAt":null,"canonicalSlug":"openrouter/auto"}},{"id":"openai/gpt-3.5-turbo-instruct","slug":"gpt-3-5-turbo-instruct","name":"OpenAI: GPT-3.5 Turbo Instruct","provider":"openai","contextLength":4095,"pricing":{"inputPerM":1.5,"outputPerM":2},"releasedAt":"2023-09-28","huggingFaceId":null,"profile":{"description":"This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021.","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs"],"maxOutput":3685,"knowledgeCutoff":"2021-09-30","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-3.5-turbo-instruct"}},{"id":"openai/gpt-3.5-turbo-16k","slug":"gpt-3-5-turbo-16k","name":"OpenAI: GPT-3.5 Turbo 16k","provider":"openai","contextLength":16385,"pricing":{"inputPerM":3,"outputPerM":4},"releasedAt":"2023-08-28","huggingFaceId":null,"profile":{"description":"This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up...","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":4096,"knowledgeCutoff":"2021-09-30","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"GPT","moderated":false,"expiresAt":null,"canonicalSlug":"openai/gpt-3.5-turbo-16k"}},{"id":"mancer/weaver","slug":"mancer-weaver","name":"Mancer: Weaver (alpha)","provider":"mancer","contextLength":8000,"pricing":{"inputPerM":0.4,"outputPerM":0.75},"releasedAt":"2023-08-02","huggingFaceId":null,"profile":{"description":"An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations.","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode"],"maxOutput":6000,"knowledgeCutoff":"2023-06-30","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Llama2","moderated":false,"expiresAt":null,"canonicalSlug":"mancer/weaver"}},{"id":"undi95/remm-slerp-l2-13b","slug":"undi95-remm-slerp-l2-13b","name":"ReMM SLERP 13B","provider":"undi95","contextLength":6144,"pricing":{"inputPerM":0.35,"outputPerM":0.65},"releasedAt":"2023-07-22","huggingFaceId":"Undi95/ReMM-SLERP-L2-13B","profile":{"description":"A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs"],"maxOutput":5529,"knowledgeCutoff":"2023-06-30","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Llama2","moderated":false,"expiresAt":null,"canonicalSlug":"undi95/remm-slerp-l2-13b"}},{"id":"gryphe/mythomax-l2-13b","slug":"gryphe-mythomax-l2-13b","name":"MythoMax 13B","provider":"gryphe","contextLength":8192,"pricing":{"inputPerM":0.08,"outputPerM":0.11},"releasedAt":"2023-07-02","huggingFaceId":"Gryphe/MythoMax-L2-13b","profile":{"description":"One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs"],"maxOutput":3686,"knowledgeCutoff":"2023-06-30","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"Llama2","moderated":false,"expiresAt":null,"canonicalSlug":"gryphe/mythomax-l2-13b"}},{"id":"openai/gpt-3.5-turbo","slug":"gpt-3-5-turbo","name":"OpenAI: GPT-3.5 Turbo","provider":"openai","contextLength":16385,"pricing":{"inputPerM":0.5,"outputPerM":1.5},"releasedAt":"2023-05-28","huggingFaceId":null,"profile":{"description":"GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021.","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":4096,"knowledgeCutoff":"2021-09-30","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"GPT","moderated":true,"expiresAt":null,"canonicalSlug":"openai/gpt-3.5-turbo"}},{"id":"openai/gpt-4","slug":"gpt-4","name":"OpenAI: GPT-4","provider":"openai","contextLength":8191,"pricing":{"inputPerM":30,"outputPerM":60},"releasedAt":"2023-05-28","huggingFaceId":null,"profile":{"description":"OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning...","inputModalities":["text"],"outputModalities":["text"],"features":["json-mode","structured-outputs","tools"],"maxOutput":4096,"knowledgeCutoff":"2021-09-30","cacheReadPerM":null,"cacheWritePerM":null,"reasoningPerM":null,"webSearchPerRequest":null,"tokenizer":"GPT","moderated":false,"expiresAt":null,"canonicalSlug":"openai/gpt-4"}}],"scores":[{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"artificialanalysis","metric":"aa_intelligence_index","value":39.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"artificialanalysis","metric":"aa_intelligence_index","value":26.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemini-4-argon","source":"artificialanalysis","metric":"aa_intelligence_index","value":52.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"stepfun/step-5-preview","source":"artificialanalysis","metric":"aa_intelligence_index","value":43.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"anthropic/claude-haiku-5.5","source":"artificialanalysis","metric":"aa_intelligence_index","value":43.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"mistralai/mistral-large-4-0","source":"artificialanalysis","metric":"aa_intelligence_index","value":38.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"inclusionai/ling-3.1-flash","source":"artificialanalysis","metric":"aa_intelligence_index","value":41.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-6.1-sol","source":"artificialanalysis","metric":"aa_intelligence_index","value":51.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"anthropic/claude-sonnet-5.5","source":"artificialanalysis","metric":"aa_intelligence_index","value":56,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"upstage/solar-mini4","source":"artificialanalysis","metric":"aa_intelligence_index","value":24.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-6-luna","source":"artificialanalysis","metric":"aa_intelligence_index","value":38.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-6-sol","source":"artificialanalysis","metric":"aa_intelligence_index","value":47.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"anthropic/claude-opus-5.5","source":"artificialanalysis","metric":"aa_intelligence_index","value":57.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"artificialanalysis","metric":"aa_intelligence_index","value":37.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"artificialanalysis","metric":"aa_intelligence_index","value":46.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"x-ai/grok-4.7","source":"artificialanalysis","metric":"aa_intelligence_index","value":46.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"inclusionai/ling-3.0-flash-vl","source":"artificialanalysis","metric":"aa_intelligence_index","value":24.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"inclusionai/ling-3.0-flash-vl","source":"artificialanalysis","metric":"aa_coding_index","value":57,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"inclusionai/ling-3.0-flash-vl","source":"artificialanalysis","metric":"aa_agentic_index","value":28.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"artificialanalysis","metric":"aa_intelligence_index","value":24.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"inception/mercury-2.5","source":"artificialanalysis","metric":"aa_intelligence_index","value":12.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-6-astra","source":"artificialanalysis","metric":"aa_intelligence_index","value":52.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-6-astra","source":"artificialanalysis","metric":"aa_coding_index","value":76.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-6-astra","source":"artificialanalysis","metric":"aa_agentic_index","value":51,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3.8-max-0902","source":"artificialanalysis","metric":"aa_intelligence_index","value":45.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3.8-max-0902","source":"artificialanalysis","metric":"aa_coding_index","value":76.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3.8-max-0902","source":"artificialanalysis","metric":"aa_agentic_index","value":56,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"meta/muse-spark-1.3","source":"artificialanalysis","metric":"aa_intelligence_index","value":48.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"meta/muse-spark-1.3","source":"artificialanalysis","metric":"aa_coding_index","value":75.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"meta/muse-spark-1.3","source":"artificialanalysis","metric":"aa_agentic_index","value":55.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemini-3.8-flash","source":"artificialanalysis","metric":"aa_intelligence_index","value":40.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemini-3.8-flash","source":"artificialanalysis","metric":"aa_coding_index","value":76.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemini-3.8-flash","source":"artificialanalysis","metric":"aa_agentic_index","value":40.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"anthropic/claude-fable-5.1","source":"artificialanalysis","metric":"aa_intelligence_index","value":53.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"anthropic/claude-fable-5.1","source":"artificialanalysis","metric":"aa_coding_index","value":81.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"anthropic/claude-fable-5.1","source":"artificialanalysis","metric":"aa_agentic_index","value":57.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"ibm-granite/granite-4.2-8b","source":"artificialanalysis","metric":"aa_intelligence_index","value":11.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"ibm-granite/granite-4.2-8b","source":"artificialanalysis","metric":"aa_coding_index","value":22.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"ibm-granite/granite-4.2-8b","source":"artificialanalysis","metric":"aa_agentic_index","value":1.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"z-ai/glm-5.3-flash","source":"artificialanalysis","metric":"aa_intelligence_index","value":41.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"z-ai/glm-5.3-flash","source":"artificialanalysis","metric":"aa_coding_index","value":71.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"z-ai/glm-5.3-flash","source":"artificialanalysis","metric":"aa_agentic_index","value":50.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"artificialanalysis","metric":"aa_intelligence_index","value":34.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"artificialanalysis","metric":"aa_coding_index","value":65,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"artificialanalysis","metric":"aa_agentic_index","value":47.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"z-ai/glm-5.3","source":"artificialanalysis","metric":"aa_intelligence_index","value":44.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"z-ai/glm-5.3","source":"artificialanalysis","metric":"aa_coding_index","value":74.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"z-ai/glm-5.3","source":"artificialanalysis","metric":"aa_agentic_index","value":53.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3.8-27b","source":"artificialanalysis","metric":"aa_intelligence_index","value":33.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3.8-27b","source":"artificialanalysis","metric":"aa_coding_index","value":68.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3.8-27b","source":"artificialanalysis","metric":"aa_agentic_index","value":45.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemini-3.7-flash","source":"artificialanalysis","metric":"aa_intelligence_index","value":39.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemini-3.7-flash","source":"artificialanalysis","metric":"aa_coding_index","value":71.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3.8-2.4t-a95b","source":"artificialanalysis","metric":"aa_intelligence_index","value":39.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3.8-2.4t-a95b","source":"artificialanalysis","metric":"aa_coding_index","value":71.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3.8-2.4t-a95b","source":"artificialanalysis","metric":"aa_agentic_index","value":50.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"artificialanalysis","metric":"aa_intelligence_index","value":36,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"artificialanalysis","metric":"aa_coding_index","value":68.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"artificialanalysis","metric":"aa_agentic_index","value":41.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"x-ai/grok-4.6","source":"artificialanalysis","metric":"aa_intelligence_index","value":44.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"x-ai/grok-4.6","source":"artificialanalysis","metric":"aa_coding_index","value":76.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"x-ai/grok-4.6","source":"artificialanalysis","metric":"aa_agentic_index","value":53,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"artificialanalysis","metric":"aa_intelligence_index","value":12.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"artificialanalysis","metric":"aa_coding_index","value":26.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"artificialanalysis","metric":"aa_agentic_index","value":3.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"upstage/solar-pro4","source":"artificialanalysis","metric":"aa_intelligence_index","value":28.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"upstage/solar-pro4","source":"artificialanalysis","metric":"aa_coding_index","value":52.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"meta/muse-glimmer-30b","source":"artificialanalysis","metric":"aa_intelligence_index","value":17.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"meta/muse-glimmer-30b","source":"artificialanalysis","metric":"aa_coding_index","value":49,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"meta/muse-glimmer-30b","source":"artificialanalysis","metric":"aa_agentic_index","value":8.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"meta/muse-spark-1.2","source":"artificialanalysis","metric":"aa_intelligence_index","value":39.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"meta/muse-spark-1.2","source":"artificialanalysis","metric":"aa_coding_index","value":72.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"meta/muse-spark-1.2","source":"artificialanalysis","metric":"aa_agentic_index","value":43.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"artificialanalysis","metric":"aa_intelligence_index","value":34.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"artificialanalysis","metric":"aa_coding_index","value":69.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"artificialanalysis","metric":"aa_agentic_index","value":41,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"thinkingmachines/inkling-small","source":"artificialanalysis","metric":"aa_intelligence_index","value":25.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"thinkingmachines/inkling-small","source":"artificialanalysis","metric":"aa_coding_index","value":52.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"thinkingmachines/inkling-small","source":"artificialanalysis","metric":"aa_agentic_index","value":23.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"anthropic/claude-opus-5","source":"artificialanalysis","metric":"aa_intelligence_index","value":50.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"anthropic/claude-opus-5","source":"artificialanalysis","metric":"aa_coding_index","value":78,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"anthropic/claude-opus-5","source":"artificialanalysis","metric":"aa_agentic_index","value":56.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"inclusionai/ling-3.0-flash","source":"artificialanalysis","metric":"aa_intelligence_index","value":20.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"inclusionai/ling-3.0-flash","source":"artificialanalysis","metric":"aa_coding_index","value":50.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"inclusionai/ling-3.0-flash","source":"artificialanalysis","metric":"aa_agentic_index","value":19.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemini-3.6-flash","source":"artificialanalysis","metric":"aa_intelligence_index","value":34,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemini-3.6-flash","source":"artificialanalysis","metric":"aa_coding_index","value":69.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemini-3.6-flash","source":"artificialanalysis","metric":"aa_agentic_index","value":29,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemini-3.5-flash-lite","source":"artificialanalysis","metric":"aa_intelligence_index","value":22.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemini-3.5-flash-lite","source":"artificialanalysis","metric":"aa_coding_index","value":49.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemini-3.5-flash-lite","source":"artificialanalysis","metric":"aa_agentic_index","value":14.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"meituan/longcat-2.0","source":"artificialanalysis","metric":"aa_intelligence_index","value":19.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"meituan/longcat-2.0","source":"artificialanalysis","metric":"aa_coding_index","value":45.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"meituan/longcat-2.0","source":"artificialanalysis","metric":"aa_agentic_index","value":14,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"thinkingmachines/inkling","source":"artificialanalysis","metric":"aa_intelligence_index","value":25,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"thinkingmachines/inkling","source":"artificialanalysis","metric":"aa_coding_index","value":52.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"thinkingmachines/inkling","source":"artificialanalysis","metric":"aa_agentic_index","value":22.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"moonshotai/kimi-k3","source":"artificialanalysis","metric":"aa_intelligence_index","value":43.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"moonshotai/kimi-k3","source":"artificialanalysis","metric":"aa_coding_index","value":76.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"moonshotai/kimi-k3","source":"artificialanalysis","metric":"aa_agentic_index","value":50,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"meta/muse-spark-1.1","source":"artificialanalysis","metric":"aa_intelligence_index","value":33.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"meta/muse-spark-1.1","source":"artificialanalysis","metric":"aa_coding_index","value":71.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"meta/muse-spark-1.1","source":"artificialanalysis","metric":"aa_agentic_index","value":25.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-5.6-luna","source":"artificialanalysis","metric":"aa_intelligence_index","value":37.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-5.6-luna","source":"artificialanalysis","metric":"aa_coding_index","value":71.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-5.6-luna","source":"artificialanalysis","metric":"aa_agentic_index","value":42.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-5.6-terra","source":"artificialanalysis","metric":"aa_intelligence_index","value":42.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-5.6-terra","source":"artificialanalysis","metric":"aa_coding_index","value":76.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-5.6-terra","source":"artificialanalysis","metric":"aa_agentic_index","value":43.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-5.6-sol","source":"artificialanalysis","metric":"aa_intelligence_index","value":47,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-5.6-sol","source":"artificialanalysis","metric":"aa_coding_index","value":77.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-5.6-sol","source":"artificialanalysis","metric":"aa_agentic_index","value":50.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"x-ai/grok-4.5","source":"artificialanalysis","metric":"aa_intelligence_index","value":38.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"x-ai/grok-4.5","source":"artificialanalysis","metric":"aa_coding_index","value":72.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"x-ai/grok-4.5","source":"artificialanalysis","metric":"aa_agentic_index","value":41.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"anthropic/claude-sonnet-5","source":"artificialanalysis","metric":"aa_intelligence_index","value":38.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"anthropic/claude-sonnet-5","source":"artificialanalysis","metric":"aa_coding_index","value":71.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"anthropic/claude-sonnet-5","source":"artificialanalysis","metric":"aa_agentic_index","value":43.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"z-ai/glm-5.2","source":"artificialanalysis","metric":"aa_intelligence_index","value":33.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"z-ai/glm-5.2","source":"artificialanalysis","metric":"aa_coding_index","value":68.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"z-ai/glm-5.2","source":"artificialanalysis","metric":"aa_agentic_index","value":38.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"moonshotai/kimi-k2.7-code","source":"artificialanalysis","metric":"aa_intelligence_index","value":25.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"moonshotai/kimi-k2.7-code","source":"artificialanalysis","metric":"aa_coding_index","value":60.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"moonshotai/kimi-k2.7-code","source":"artificialanalysis","metric":"aa_agentic_index","value":21,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"anthropic/claude-fable-5","source":"artificialanalysis","metric":"aa_intelligence_index","value":49.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"anthropic/claude-fable-5","source":"artificialanalysis","metric":"aa_coding_index","value":76.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"anthropic/claude-fable-5","source":"artificialanalysis","metric":"aa_agentic_index","value":50.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"artificialanalysis","metric":"aa_intelligence_index","value":22.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"artificialanalysis","metric":"aa_coding_index","value":49.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"artificialanalysis","metric":"aa_agentic_index","value":20.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3.7-plus","source":"artificialanalysis","metric":"aa_intelligence_index","value":25.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3.7-plus","source":"artificialanalysis","metric":"aa_coding_index","value":55.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3.7-plus","source":"artificialanalysis","metric":"aa_agentic_index","value":17.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"minimax/minimax-m3","source":"artificialanalysis","metric":"aa_intelligence_index","value":29.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"minimax/minimax-m3","source":"artificialanalysis","metric":"aa_coding_index","value":58.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"minimax/minimax-m3","source":"artificialanalysis","metric":"aa_agentic_index","value":29.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"stepfun/step-3.7-flash","source":"artificialanalysis","metric":"aa_intelligence_index","value":19.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"stepfun/step-3.7-flash","source":"artificialanalysis","metric":"aa_coding_index","value":39.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"anthropic/claude-opus-4.8","source":"artificialanalysis","metric":"aa_intelligence_index","value":41.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"anthropic/claude-opus-4.8","source":"artificialanalysis","metric":"aa_coding_index","value":74.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"anthropic/claude-opus-4.8","source":"artificialanalysis","metric":"aa_agentic_index","value":41.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3.7-max","source":"artificialanalysis","metric":"aa_intelligence_index","value":29.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3.7-max","source":"artificialanalysis","metric":"aa_coding_index","value":66,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3.7-max","source":"artificialanalysis","metric":"aa_agentic_index","value":22.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"x-ai/grok-build-0.1","source":"artificialanalysis","metric":"aa_intelligence_index","value":27.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"x-ai/grok-build-0.1","source":"artificialanalysis","metric":"aa_coding_index","value":51.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemini-3.5-flash","source":"artificialanalysis","metric":"aa_intelligence_index","value":33.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"x-ai/grok-4.3","source":"artificialanalysis","metric":"aa_intelligence_index","value":24.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"x-ai/grok-4.3","source":"artificialanalysis","metric":"aa_coding_index","value":42.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"x-ai/grok-4.3","source":"artificialanalysis","metric":"aa_agentic_index","value":15.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"mistralai/mistral-medium-3-5","source":"artificialanalysis","metric":"aa_intelligence_index","value":14.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"mistralai/mistral-medium-3-5","source":"artificialanalysis","metric":"aa_coding_index","value":46.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"mistralai/mistral-medium-3-5","source":"artificialanalysis","metric":"aa_agentic_index","value":7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3.6-35b-a3b","source":"artificialanalysis","metric":"aa_intelligence_index","value":18.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3.6-35b-a3b","source":"artificialanalysis","metric":"aa_coding_index","value":41.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3.6-35b-a3b","source":"artificialanalysis","metric":"aa_agentic_index","value":13.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3.6-27b","source":"artificialanalysis","metric":"aa_intelligence_index","value":21.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3.6-27b","source":"artificialanalysis","metric":"aa_coding_index","value":53.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3.6-27b","source":"artificialanalysis","metric":"aa_agentic_index","value":18.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-5.5","source":"artificialanalysis","metric":"aa_intelligence_index","value":38.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-5.5","source":"artificialanalysis","metric":"aa_coding_index","value":74.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-5.5","source":"artificialanalysis","metric":"aa_agentic_index","value":36.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"deepseek/deepseek-v4-pro","source":"artificialanalysis","metric":"aa_intelligence_index","value":30.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"deepseek/deepseek-v4-pro","source":"artificialanalysis","metric":"aa_coding_index","value":59.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"deepseek/deepseek-v4-pro","source":"artificialanalysis","metric":"aa_agentic_index","value":26.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"deepseek/deepseek-v4-flash","source":"artificialanalysis","metric":"aa_intelligence_index","value":24.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"deepseek/deepseek-v4-flash","source":"artificialanalysis","metric":"aa_coding_index","value":52,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"deepseek/deepseek-v4-flash","source":"artificialanalysis","metric":"aa_agentic_index","value":26.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"tencent/hy3-preview","source":"artificialanalysis","metric":"aa_intelligence_index","value":25.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"tencent/hy3-preview","source":"artificialanalysis","metric":"aa_coding_index","value":58.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"tencent/hy3-preview","source":"artificialanalysis","metric":"aa_agentic_index","value":24.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"artificialanalysis","metric":"aa_intelligence_index","value":26,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"artificialanalysis","metric":"aa_coding_index","value":60.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"artificialanalysis","metric":"aa_agentic_index","value":21.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"xiaomi/mimo-v2.5","source":"artificialanalysis","metric":"aa_intelligence_index","value":21.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"xiaomi/mimo-v2.5","source":"artificialanalysis","metric":"aa_coding_index","value":56.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"xiaomi/mimo-v2.5","source":"artificialanalysis","metric":"aa_agentic_index","value":15.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"moonshotai/kimi-k2.6","source":"artificialanalysis","metric":"aa_intelligence_index","value":27,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"moonshotai/kimi-k2.6","source":"artificialanalysis","metric":"aa_coding_index","value":61.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"moonshotai/kimi-k2.6","source":"artificialanalysis","metric":"aa_agentic_index","value":20.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"anthropic/claude-opus-4.7","source":"artificialanalysis","metric":"aa_intelligence_index","value":40.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"anthropic/claude-opus-4.7","source":"artificialanalysis","metric":"aa_coding_index","value":73.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"anthropic/claude-opus-4.7","source":"artificialanalysis","metric":"aa_agentic_index","value":38.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"z-ai/glm-5.1","source":"artificialanalysis","metric":"aa_intelligence_index","value":26.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"z-ai/glm-5.1","source":"artificialanalysis","metric":"aa_coding_index","value":55.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"z-ai/glm-5.1","source":"artificialanalysis","metric":"aa_agentic_index","value":23.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemma-4-26b-a4b-it","source":"artificialanalysis","metric":"aa_intelligence_index","value":16.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemma-4-26b-a4b-it","source":"artificialanalysis","metric":"aa_coding_index","value":39.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemma-4-26b-a4b-it","source":"artificialanalysis","metric":"aa_agentic_index","value":2.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemma-4-31b-it","source":"artificialanalysis","metric":"aa_intelligence_index","value":14.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemma-4-31b-it","source":"artificialanalysis","metric":"aa_coding_index","value":43.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemma-4-31b-it","source":"artificialanalysis","metric":"aa_agentic_index","value":4.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3.6-plus","source":"artificialanalysis","metric":"aa_intelligence_index","value":27,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3.6-plus","source":"artificialanalysis","metric":"aa_coding_index","value":54.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"z-ai/glm-5v-turbo","source":"artificialanalysis","metric":"aa_intelligence_index","value":23.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"arcee-ai/trinity-large-thinking","source":"artificialanalysis","metric":"aa_intelligence_index","value":10.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"arcee-ai/trinity-large-thinking","source":"artificialanalysis","metric":"aa_coding_index","value":25.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"arcee-ai/trinity-large-thinking","source":"artificialanalysis","metric":"aa_agentic_index","value":1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"x-ai/grok-4.20","source":"artificialanalysis","metric":"aa_intelligence_index","value":25.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"minimax/minimax-m2.7","source":"artificialanalysis","metric":"aa_intelligence_index","value":22.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"minimax/minimax-m2.7","source":"artificialanalysis","metric":"aa_coding_index","value":52.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"minimax/minimax-m2.7","source":"artificialanalysis","metric":"aa_agentic_index","value":15.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-5.4-nano","source":"artificialanalysis","metric":"aa_intelligence_index","value":20.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-5.4-nano","source":"artificialanalysis","metric":"aa_coding_index","value":56.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-5.4-nano","source":"artificialanalysis","metric":"aa_agentic_index","value":16,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-5.4-mini","source":"artificialanalysis","metric":"aa_intelligence_index","value":24.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-5.4-mini","source":"artificialanalysis","metric":"aa_coding_index","value":56.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-5.4-mini","source":"artificialanalysis","metric":"aa_agentic_index","value":17.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"mistralai/mistral-small-2603","source":"artificialanalysis","metric":"aa_intelligence_index","value":11.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"mistralai/mistral-small-2603","source":"artificialanalysis","metric":"aa_coding_index","value":26.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"mistralai/mistral-small-2603","source":"artificialanalysis","metric":"aa_agentic_index","value":0.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"z-ai/glm-5-turbo","source":"artificialanalysis","metric":"aa_intelligence_index","value":26.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"artificialanalysis","metric":"aa_intelligence_index","value":12.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"artificialanalysis","metric":"aa_coding_index","value":37.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"artificialanalysis","metric":"aa_agentic_index","value":1.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3.5-9b","source":"artificialanalysis","metric":"aa_intelligence_index","value":13.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3.5-9b","source":"artificialanalysis","metric":"aa_coding_index","value":23.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-5.4","source":"artificialanalysis","metric":"aa_intelligence_index","value":39,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-5.4","source":"artificialanalysis","metric":"aa_coding_index","value":71.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"inception/mercury-2","source":"artificialanalysis","metric":"aa_intelligence_index","value":10.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"inception/mercury-2","source":"artificialanalysis","metric":"aa_coding_index","value":31.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"inception/mercury-2","source":"artificialanalysis","metric":"aa_agentic_index","value":1.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"artificialanalysis","metric":"aa_intelligence_index","value":15.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"artificialanalysis","metric":"aa_coding_index","value":34.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"artificialanalysis","metric":"aa_agentic_index","value":1.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"artificialanalysis","metric":"aa_intelligence_index","value":19.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3.5-27b","source":"artificialanalysis","metric":"aa_intelligence_index","value":22.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"artificialanalysis","metric":"aa_intelligence_index","value":17.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"artificialanalysis","metric":"aa_coding_index","value":43.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-5.3-codex","source":"artificialanalysis","metric":"aa_intelligence_index","value":32.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemini-3.1-pro-preview","source":"artificialanalysis","metric":"aa_intelligence_index","value":29.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemini-3.1-pro-preview","source":"artificialanalysis","metric":"aa_coding_index","value":68.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemini-3.1-pro-preview","source":"artificialanalysis","metric":"aa_agentic_index","value":8.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"anthropic/claude-sonnet-4.6","source":"artificialanalysis","metric":"aa_intelligence_index","value":30.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"anthropic/claude-sonnet-4.6","source":"artificialanalysis","metric":"aa_coding_index","value":63,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"anthropic/claude-sonnet-4.6","source":"artificialanalysis","metric":"aa_agentic_index","value":31.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"artificialanalysis","metric":"aa_intelligence_index","value":21.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"minimax/minimax-m2.5","source":"artificialanalysis","metric":"aa_intelligence_index","value":22.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"z-ai/glm-5","source":"artificialanalysis","metric":"aa_intelligence_index","value":27.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"anthropic/claude-opus-4.6","source":"artificialanalysis","metric":"aa_intelligence_index","value":31.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3-coder-next","source":"artificialanalysis","metric":"aa_intelligence_index","value":9.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3-coder-next","source":"artificialanalysis","metric":"aa_coding_index","value":36.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3-coder-next","source":"artificialanalysis","metric":"aa_agentic_index","value":0.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"stepfun/step-3.5-flash","source":"artificialanalysis","metric":"aa_intelligence_index","value":17,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"moonshotai/kimi-k2.5","source":"artificialanalysis","metric":"aa_intelligence_index","value":23.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"moonshotai/kimi-k2.5","source":"artificialanalysis","metric":"aa_coding_index","value":46.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"upstage/solar-pro-3","source":"artificialanalysis","metric":"aa_intelligence_index","value":7.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"upstage/solar-pro-3","source":"artificialanalysis","metric":"aa_coding_index","value":16.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"upstage/solar-pro-3","source":"artificialanalysis","metric":"aa_agentic_index","value":1.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"z-ai/glm-4.7-flash","source":"artificialanalysis","metric":"aa_intelligence_index","value":14.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-5.2-codex","source":"artificialanalysis","metric":"aa_intelligence_index","value":28.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"minimax/minimax-m2.1","source":"artificialanalysis","metric":"aa_intelligence_index","value":20.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"z-ai/glm-4.7","source":"artificialanalysis","metric":"aa_intelligence_index","value":22.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"z-ai/glm-4.7","source":"artificialanalysis","metric":"aa_coding_index","value":45.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemini-3-flash-preview","source":"artificialanalysis","metric":"aa_intelligence_index","value":26.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"nvidia/nemotron-3-nano-30b-a3b","source":"artificialanalysis","metric":"aa_intelligence_index","value":8.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"nvidia/nemotron-3-nano-30b-a3b","source":"artificialanalysis","metric":"aa_coding_index","value":14.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"nvidia/nemotron-3-nano-30b-a3b","source":"artificialanalysis","metric":"aa_agentic_index","value":1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-5.2","source":"artificialanalysis","metric":"aa_intelligence_index","value":30.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"mistralai/devstral-2512","source":"artificialanalysis","metric":"aa_intelligence_index","value":8.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"mistralai/devstral-2512","source":"artificialanalysis","metric":"aa_coding_index","value":31.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"mistralai/devstral-2512","source":"artificialanalysis","metric":"aa_agentic_index","value":2.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"z-ai/glm-4.6v","source":"artificialanalysis","metric":"aa_intelligence_index","value":11.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"amazon/nova-2-lite-v1","source":"artificialanalysis","metric":"aa_intelligence_index","value":13.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"amazon/nova-2-lite-v1","source":"artificialanalysis","metric":"aa_coding_index","value":23,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"mistralai/ministral-14b-2512","source":"artificialanalysis","metric":"aa_intelligence_index","value":6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"mistralai/ministral-14b-2512","source":"artificialanalysis","metric":"aa_coding_index","value":14.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"mistralai/ministral-14b-2512","source":"artificialanalysis","metric":"aa_agentic_index","value":1.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"mistralai/ministral-8b-2512","source":"artificialanalysis","metric":"aa_intelligence_index","value":5.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"mistralai/ministral-8b-2512","source":"artificialanalysis","metric":"aa_coding_index","value":9.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"mistralai/ministral-8b-2512","source":"artificialanalysis","metric":"aa_agentic_index","value":0.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"mistralai/ministral-3b-2512","source":"artificialanalysis","metric":"aa_intelligence_index","value":4.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"mistralai/ministral-3b-2512","source":"artificialanalysis","metric":"aa_coding_index","value":4.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"mistralai/ministral-3b-2512","source":"artificialanalysis","metric":"aa_agentic_index","value":0.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"mistralai/mistral-large-2512","source":"artificialanalysis","metric":"aa_intelligence_index","value":9.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"mistralai/mistral-large-2512","source":"artificialanalysis","metric":"aa_coding_index","value":20.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"mistralai/mistral-large-2512","source":"artificialanalysis","metric":"aa_agentic_index","value":1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"deepseek/deepseek-v3.2","source":"artificialanalysis","metric":"aa_intelligence_index","value":21.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"deepseek/deepseek-v3.2","source":"artificialanalysis","metric":"aa_coding_index","value":44.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"anthropic/claude-opus-4.5","source":"artificialanalysis","metric":"aa_intelligence_index","value":29.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-5.1","source":"artificialanalysis","metric":"aa_intelligence_index","value":24.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-5.1","source":"artificialanalysis","metric":"aa_coding_index","value":49.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-5.1-codex","source":"artificialanalysis","metric":"aa_intelligence_index","value":23.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-5.1-codex-mini","source":"artificialanalysis","metric":"aa_intelligence_index","value":20.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"moonshotai/kimi-k2-thinking","source":"artificialanalysis","metric":"aa_intelligence_index","value":22,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"amazon/nova-premier-v1","source":"artificialanalysis","metric":"aa_intelligence_index","value":9.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"minimax/minimax-m2","source":"artificialanalysis","metric":"aa_intelligence_index","value":18.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"ibm-granite/granite-4.0-h-micro","source":"artificialanalysis","metric":"aa_intelligence_index","value":5.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"anthropic/claude-haiku-4.5","source":"artificialanalysis","metric":"aa_intelligence_index","value":16.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"anthropic/claude-haiku-4.5","source":"artificialanalysis","metric":"aa_coding_index","value":43.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"anthropic/claude-haiku-4.5","source":"artificialanalysis","metric":"aa_agentic_index","value":8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3-vl-8b-instruct","source":"artificialanalysis","metric":"aa_intelligence_index","value":7.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3-vl-30b-a3b-thinking","source":"artificialanalysis","metric":"aa_intelligence_index","value":9.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3-vl-30b-a3b-instruct","source":"artificialanalysis","metric":"aa_intelligence_index","value":7.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"z-ai/glm-4.6","source":"artificialanalysis","metric":"aa_intelligence_index","value":18.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"z-ai/glm-4.6","source":"artificialanalysis","metric":"aa_coding_index","value":45.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"anthropic/claude-sonnet-4.5","source":"artificialanalysis","metric":"aa_intelligence_index","value":20.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"anthropic/claude-sonnet-4.5","source":"artificialanalysis","metric":"aa_coding_index","value":52.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"anthropic/claude-sonnet-4.5","source":"artificialanalysis","metric":"aa_agentic_index","value":15.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"artificialanalysis","metric":"aa_intelligence_index","value":16.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"artificialanalysis","metric":"aa_intelligence_index","value":9.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"artificialanalysis","metric":"aa_intelligence_index","value":14.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"artificialanalysis","metric":"aa_coding_index","value":43.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"artificialanalysis","metric":"aa_agentic_index","value":6.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"artificialanalysis","metric":"aa_intelligence_index","value":11.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"artificialanalysis","metric":"aa_coding_index","value":17.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"artificialanalysis","metric":"aa_intelligence_index","value":9.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"moonshotai/kimi-k2-0905","source":"artificialanalysis","metric":"aa_intelligence_index","value":15.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"nousresearch/hermes-4-405b","source":"artificialanalysis","metric":"aa_intelligence_index","value":7.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"deepseek/deepseek-chat-v3.1","source":"artificialanalysis","metric":"aa_intelligence_index","value":13.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"mistralai/mistral-medium-3.1","source":"artificialanalysis","metric":"aa_intelligence_index","value":9.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"mistralai/mistral-medium-3.1","source":"artificialanalysis","metric":"aa_coding_index","value":20.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"mistralai/mistral-medium-3.1","source":"artificialanalysis","metric":"aa_agentic_index","value":1.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"z-ai/glm-4.5v","source":"artificialanalysis","metric":"aa_intelligence_index","value":7.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-5","source":"artificialanalysis","metric":"aa_intelligence_index","value":23,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-5","source":"artificialanalysis","metric":"aa_coding_index","value":37.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-5-mini","source":"artificialanalysis","metric":"aa_intelligence_index","value":20.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-5-nano","source":"artificialanalysis","metric":"aa_intelligence_index","value":13,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-oss-120b","source":"artificialanalysis","metric":"aa_intelligence_index","value":11.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-oss-120b","source":"artificialanalysis","metric":"aa_coding_index","value":30.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-oss-120b","source":"artificialanalysis","metric":"aa_agentic_index","value":3.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-oss-20b","source":"artificialanalysis","metric":"aa_intelligence_index","value":10,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"anthropic/claude-opus-4.1","source":"artificialanalysis","metric":"aa_intelligence_index","value":22.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3-coder-30b-a3b-instruct","source":"artificialanalysis","metric":"aa_intelligence_index","value":9.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"artificialanalysis","metric":"aa_intelligence_index","value":7.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"z-ai/glm-4.5","source":"artificialanalysis","metric":"aa_intelligence_index","value":12.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"z-ai/glm-4.5-air","source":"artificialanalysis","metric":"aa_intelligence_index","value":11.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"artificialanalysis","metric":"aa_intelligence_index","value":12.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"artificialanalysis","metric":"aa_coding_index","value":22.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"artificialanalysis","metric":"aa_agentic_index","value":1.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3-coder","source":"artificialanalysis","metric":"aa_intelligence_index","value":11.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemini-2.5-flash-lite","source":"artificialanalysis","metric":"aa_intelligence_index","value":10.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"artificialanalysis","metric":"aa_intelligence_index","value":12,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"moonshotai/kimi-k2","source":"artificialanalysis","metric":"aa_intelligence_index","value":12.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"minimax/minimax-m1","source":"artificialanalysis","metric":"aa_intelligence_index","value":11.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemini-2.5-flash","source":"artificialanalysis","metric":"aa_intelligence_index","value":15.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemini-2.5-pro","source":"artificialanalysis","metric":"aa_intelligence_index","value":16.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemini-2.5-pro","source":"artificialanalysis","metric":"aa_coding_index","value":33.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemini-2.5-pro","source":"artificialanalysis","metric":"aa_agentic_index","value":1.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/o3-pro","source":"artificialanalysis","metric":"aa_intelligence_index","value":21.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"deepseek/deepseek-r1-0528","source":"artificialanalysis","metric":"aa_intelligence_index","value":13.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"mistralai/mistral-medium-3","source":"artificialanalysis","metric":"aa_intelligence_index","value":9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3-30b-a3b","source":"artificialanalysis","metric":"aa_intelligence_index","value":7.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3-14b","source":"artificialanalysis","metric":"aa_intelligence_index","value":6.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen3-32b","source":"artificialanalysis","metric":"aa_intelligence_index","value":7.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/o3","source":"artificialanalysis","metric":"aa_intelligence_index","value":20.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/o4-mini","source":"artificialanalysis","metric":"aa_intelligence_index","value":16.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-4.1","source":"artificialanalysis","metric":"aa_intelligence_index","value":12.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-4.1-mini","source":"artificialanalysis","metric":"aa_intelligence_index","value":10.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-4.1-mini","source":"artificialanalysis","metric":"aa_coding_index","value":20.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-4.1-nano","source":"artificialanalysis","metric":"aa_intelligence_index","value":7.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-4.1-nano","source":"artificialanalysis","metric":"aa_coding_index","value":11.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"meta-llama/llama-4-maverick","source":"artificialanalysis","metric":"aa_intelligence_index","value":9.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"meta-llama/llama-4-maverick","source":"artificialanalysis","metric":"aa_coding_index","value":16.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"meta-llama/llama-4-maverick","source":"artificialanalysis","metric":"aa_agentic_index","value":0.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"meta-llama/llama-4-scout","source":"artificialanalysis","metric":"aa_intelligence_index","value":6.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"meta-llama/llama-4-scout","source":"artificialanalysis","metric":"aa_coding_index","value":8.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"meta-llama/llama-4-scout","source":"artificialanalysis","metric":"aa_agentic_index","value":0.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"artificialanalysis","metric":"aa_intelligence_index","value":9.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"artificialanalysis","metric":"aa_coding_index","value":21.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"artificialanalysis","metric":"aa_agentic_index","value":0.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/o1-pro","source":"artificialanalysis","metric":"aa_intelligence_index","value":12.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemma-3-4b-it","source":"artificialanalysis","metric":"aa_intelligence_index","value":4.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemma-3-4b-it","source":"artificialanalysis","metric":"aa_coding_index","value":2.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemma-3-12b-it","source":"artificialanalysis","metric":"aa_intelligence_index","value":3.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemma-3-12b-it","source":"artificialanalysis","metric":"aa_coding_index","value":5.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemma-3-12b-it","source":"artificialanalysis","metric":"aa_agentic_index","value":0.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"cohere/command-a","source":"artificialanalysis","metric":"aa_intelligence_index","value":13.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"cohere/command-a","source":"artificialanalysis","metric":"aa_coding_index","value":27.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"cohere/command-a","source":"artificialanalysis","metric":"aa_agentic_index","value":1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"rekaai/reka-flash-3","source":"artificialanalysis","metric":"aa_intelligence_index","value":6.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemma-3-27b-it","source":"artificialanalysis","metric":"aa_intelligence_index","value":4.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemma-3-27b-it","source":"artificialanalysis","metric":"aa_coding_index","value":10.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"google/gemma-3-27b-it","source":"artificialanalysis","metric":"aa_agentic_index","value":0.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"perplexity/sonar-reasoning-pro","source":"artificialanalysis","metric":"aa_intelligence_index","value":11.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"perplexity/sonar-pro","source":"artificialanalysis","metric":"aa_intelligence_index","value":7.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"mistralai/mistral-saba","source":"artificialanalysis","metric":"aa_intelligence_index","value":6.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/o3-mini-high","source":"artificialanalysis","metric":"aa_intelligence_index","value":11,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/o3-mini-high","source":"artificialanalysis","metric":"aa_coding_index","value":16.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/o3-mini-high","source":"artificialanalysis","metric":"aa_agentic_index","value":0.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/o3-mini","source":"artificialanalysis","metric":"aa_intelligence_index","value":12.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"artificialanalysis","metric":"aa_intelligence_index","value":6.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"perplexity/sonar","source":"artificialanalysis","metric":"aa_intelligence_index","value":7.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"microsoft/phi-4","source":"artificialanalysis","metric":"aa_intelligence_index","value":5.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/o1","source":"artificialanalysis","metric":"aa_intelligence_index","value":15.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/o1","source":"artificialanalysis","metric":"aa_coding_index","value":39.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"artificialanalysis","metric":"aa_intelligence_index","value":7.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"artificialanalysis","metric":"aa_coding_index","value":11.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"amazon/nova-lite-v1","source":"artificialanalysis","metric":"aa_intelligence_index","value":6.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"amazon/nova-micro-v1","source":"artificialanalysis","metric":"aa_intelligence_index","value":5.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"amazon/nova-pro-v1","source":"artificialanalysis","metric":"aa_intelligence_index","value":7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-4o-2024-11-20","source":"artificialanalysis","metric":"aa_intelligence_index","value":8.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"mistralai/mistral-large-2407","source":"artificialanalysis","metric":"aa_intelligence_index","value":7.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"artificialanalysis","metric":"aa_intelligence_index","value":6.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"artificialanalysis","metric":"aa_intelligence_index","value":4.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"artificialanalysis","metric":"aa_intelligence_index","value":5.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"artificialanalysis","metric":"aa_intelligence_index","value":7.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"nousresearch/hermes-3-llama-3.1-70b","source":"artificialanalysis","metric":"aa_intelligence_index","value":6.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-4o-2024-08-06","source":"artificialanalysis","metric":"aa_intelligence_index","value":7.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"artificialanalysis","metric":"aa_intelligence_index","value":6.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"artificialanalysis","metric":"aa_intelligence_index","value":6.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"artificialanalysis","metric":"aa_coding_index","value":5.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-4o-mini","source":"artificialanalysis","metric":"aa_intelligence_index","value":6.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-4o-mini","source":"artificialanalysis","metric":"aa_coding_index","value":11.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-4o-2024-05-13","source":"artificialanalysis","metric":"aa_intelligence_index","value":7.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-4o-2024-05-13","source":"artificialanalysis","metric":"aa_coding_index","value":24.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"mistralai/mixtral-8x22b-instruct","source":"artificialanalysis","metric":"aa_intelligence_index","value":5.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-4-turbo","source":"artificialanalysis","metric":"aa_intelligence_index","value":7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-4-turbo","source":"artificialanalysis","metric":"aa_coding_index","value":21.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"mistralai/mistral-large","source":"artificialanalysis","metric":"aa_intelligence_index","value":5.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-3.5-turbo","source":"artificialanalysis","metric":"aa_intelligence_index","value":5.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-3.5-turbo","source":"artificialanalysis","metric":"aa_coding_index","value":10.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-4","source":"artificialanalysis","metric":"aa_intelligence_index","value":6.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-4","source":"artificialanalysis","metric":"aa_coding_index","value":13.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/models"},{"modelId":"openai/gpt-5","source":"aider","metric":"polyglot_pass_rate","value":0.88,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-5","source":"aider","metric":"polyglot_run_cost_usd","value":29.08,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-5","source":"aider","metric":"polyglot_first_try_rate","value":0.52,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-5","source":"aider","metric":"polyglot_well_formed_rate","value":0.916,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-5","source":"aider","metric":"polyglot_solved_count","value":198,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-5","source":"aider","metric":"polyglot_test_cases","value":225,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-5","source":"aider","metric":"polyglot_prompt_tokens","value":2675561,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-5","source":"aider","metric":"polyglot_completion_tokens","value":2623429,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-5","source":"aider","metric":"polyglot_seconds_per_case","value":194,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o3-pro","source":"aider","metric":"polyglot_pass_rate","value":0.8490000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o3-pro","source":"aider","metric":"polyglot_run_cost_usd","value":146.32,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o3-pro","source":"aider","metric":"polyglot_first_try_rate","value":0.436,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o3-pro","source":"aider","metric":"polyglot_well_formed_rate","value":0.978,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o3-pro","source":"aider","metric":"polyglot_solved_count","value":191,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o3-pro","source":"aider","metric":"polyglot_test_cases","value":225,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o3-pro","source":"aider","metric":"polyglot_prompt_tokens","value":2372636,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o3-pro","source":"aider","metric":"polyglot_completion_tokens","value":1235902,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o3-pro","source":"aider","metric":"polyglot_seconds_per_case","value":449,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"google/gemini-2.5-pro-preview","source":"aider","metric":"polyglot_pass_rate","value":0.831,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"google/gemini-2.5-pro-preview","source":"aider","metric":"polyglot_run_cost_usd","value":49.88,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"google/gemini-2.5-pro-preview","source":"aider","metric":"polyglot_first_try_rate","value":0.462,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"google/gemini-2.5-pro-preview","source":"aider","metric":"polyglot_well_formed_rate","value":0.996,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"google/gemini-2.5-pro-preview","source":"aider","metric":"polyglot_solved_count","value":187,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"google/gemini-2.5-pro-preview","source":"aider","metric":"polyglot_test_cases","value":225,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"google/gemini-2.5-pro-preview","source":"aider","metric":"polyglot_prompt_tokens","value":2719961,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"google/gemini-2.5-pro-preview","source":"aider","metric":"polyglot_completion_tokens","value":4648227,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"google/gemini-2.5-pro-preview","source":"aider","metric":"polyglot_seconds_per_case","value":200.3,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o3","source":"aider","metric":"polyglot_pass_rate","value":0.813,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o3","source":"aider","metric":"polyglot_run_cost_usd","value":21.23,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o3","source":"aider","metric":"polyglot_first_try_rate","value":0.4,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o3","source":"aider","metric":"polyglot_well_formed_rate","value":0.947,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o3","source":"aider","metric":"polyglot_solved_count","value":183,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o3","source":"aider","metric":"polyglot_test_cases","value":225,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o3","source":"aider","metric":"polyglot_prompt_tokens","value":3148932,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o3","source":"aider","metric":"polyglot_completion_tokens","value":2047615,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o3","source":"aider","metric":"polyglot_seconds_per_case","value":197.3,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"aider","metric":"polyglot_pass_rate","value":0.742,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"aider","metric":"polyglot_run_cost_usd","value":1.3,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"aider","metric":"polyglot_first_try_rate","value":0.396,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"aider","metric":"polyglot_well_formed_rate","value":0.973,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"aider","metric":"polyglot_solved_count","value":167,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"aider","metric":"polyglot_test_cases","value":225,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"aider","metric":"polyglot_prompt_tokens","value":2191446,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"aider","metric":"polyglot_completion_tokens","value":1645129,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"aider","metric":"polyglot_seconds_per_case","value":291.2,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o4-mini","source":"aider","metric":"polyglot_pass_rate","value":0.72,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o4-mini","source":"aider","metric":"polyglot_run_cost_usd","value":19.64,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o4-mini","source":"aider","metric":"polyglot_first_try_rate","value":0.196,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o4-mini","source":"aider","metric":"polyglot_well_formed_rate","value":0.907,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o4-mini","source":"aider","metric":"polyglot_solved_count","value":162,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o4-mini","source":"aider","metric":"polyglot_test_cases","value":225,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o4-mini","source":"aider","metric":"polyglot_seconds_per_case","value":176.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"deepseek/deepseek-r1-0528","source":"aider","metric":"polyglot_pass_rate","value":0.7140000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"deepseek/deepseek-r1-0528","source":"aider","metric":"polyglot_run_cost_usd","value":4.8,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"deepseek/deepseek-r1-0528","source":"aider","metric":"polyglot_first_try_rate","value":0.344,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"deepseek/deepseek-r1-0528","source":"aider","metric":"polyglot_well_formed_rate","value":0.946,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"deepseek/deepseek-r1-0528","source":"aider","metric":"polyglot_solved_count","value":160,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"deepseek/deepseek-r1-0528","source":"aider","metric":"polyglot_test_cases","value":224,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"deepseek/deepseek-r1-0528","source":"aider","metric":"polyglot_prompt_tokens","value":2644169,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"deepseek/deepseek-r1-0528","source":"aider","metric":"polyglot_completion_tokens","value":1842168,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"deepseek/deepseek-r1-0528","source":"aider","metric":"polyglot_seconds_per_case","value":716.6,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"deepseek/deepseek-chat","source":"aider","metric":"polyglot_pass_rate","value":0.7020000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"deepseek/deepseek-chat","source":"aider","metric":"polyglot_run_cost_usd","value":0.88,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"deepseek/deepseek-chat","source":"aider","metric":"polyglot_first_try_rate","value":0.387,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"deepseek/deepseek-chat","source":"aider","metric":"polyglot_well_formed_rate","value":0.982,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"deepseek/deepseek-chat","source":"aider","metric":"polyglot_solved_count","value":158,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"deepseek/deepseek-chat","source":"aider","metric":"polyglot_test_cases","value":225,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"deepseek/deepseek-chat","source":"aider","metric":"polyglot_prompt_tokens","value":2266868,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"deepseek/deepseek-chat","source":"aider","metric":"polyglot_completion_tokens","value":573477,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"deepseek/deepseek-chat","source":"aider","metric":"polyglot_seconds_per_case","value":104,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o1","source":"aider","metric":"polyglot_pass_rate","value":0.617,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o1","source":"aider","metric":"polyglot_run_cost_usd","value":186.5,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o1","source":"aider","metric":"polyglot_first_try_rate","value":0.237,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o1","source":"aider","metric":"polyglot_well_formed_rate","value":0.915,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o1","source":"aider","metric":"polyglot_solved_count","value":139,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o1","source":"aider","metric":"polyglot_test_cases","value":224,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o1","source":"aider","metric":"polyglot_seconds_per_case","value":133.2,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o3-mini","source":"aider","metric":"polyglot_pass_rate","value":0.604,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o3-mini","source":"aider","metric":"polyglot_run_cost_usd","value":18.16,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o3-mini","source":"aider","metric":"polyglot_first_try_rate","value":0.21,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o3-mini","source":"aider","metric":"polyglot_well_formed_rate","value":0.933,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o3-mini","source":"aider","metric":"polyglot_solved_count","value":136,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o3-mini","source":"aider","metric":"polyglot_test_cases","value":224,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/o3-mini","source":"aider","metric":"polyglot_seconds_per_case","value":124.6,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"moonshotai/kimi-k2","source":"aider","metric":"polyglot_pass_rate","value":0.591,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"moonshotai/kimi-k2","source":"aider","metric":"polyglot_run_cost_usd","value":1.24,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"moonshotai/kimi-k2","source":"aider","metric":"polyglot_first_try_rate","value":0.204,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"moonshotai/kimi-k2","source":"aider","metric":"polyglot_well_formed_rate","value":0.929,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"moonshotai/kimi-k2","source":"aider","metric":"polyglot_solved_count","value":133,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"moonshotai/kimi-k2","source":"aider","metric":"polyglot_test_cases","value":225,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"moonshotai/kimi-k2","source":"aider","metric":"polyglot_prompt_tokens","value":2355141,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"moonshotai/kimi-k2","source":"aider","metric":"polyglot_completion_tokens","value":363846,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"moonshotai/kimi-k2","source":"aider","metric":"polyglot_seconds_per_case","value":67.6,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4.1","source":"aider","metric":"polyglot_pass_rate","value":0.524,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4.1","source":"aider","metric":"polyglot_run_cost_usd","value":9.86,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4.1","source":"aider","metric":"polyglot_first_try_rate","value":0.2,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4.1","source":"aider","metric":"polyglot_well_formed_rate","value":0.982,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4.1","source":"aider","metric":"polyglot_solved_count","value":118,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4.1","source":"aider","metric":"polyglot_test_cases","value":225,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4.1","source":"aider","metric":"polyglot_seconds_per_case","value":20.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-oss-120b","source":"aider","metric":"polyglot_pass_rate","value":0.418,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-oss-120b","source":"aider","metric":"polyglot_run_cost_usd","value":0.74,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-oss-120b","source":"aider","metric":"polyglot_first_try_rate","value":0.138,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-oss-120b","source":"aider","metric":"polyglot_well_formed_rate","value":0.791,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-oss-120b","source":"aider","metric":"polyglot_solved_count","value":94,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-oss-120b","source":"aider","metric":"polyglot_test_cases","value":225,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-oss-120b","source":"aider","metric":"polyglot_prompt_tokens","value":3123768,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-oss-120b","source":"aider","metric":"polyglot_completion_tokens","value":856495,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-oss-120b","source":"aider","metric":"polyglot_seconds_per_case","value":35.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"qwen/qwen3-32b","source":"aider","metric":"polyglot_pass_rate","value":0.4,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"qwen/qwen3-32b","source":"aider","metric":"polyglot_run_cost_usd","value":0.76,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"qwen/qwen3-32b","source":"aider","metric":"polyglot_first_try_rate","value":0.142,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"qwen/qwen3-32b","source":"aider","metric":"polyglot_well_formed_rate","value":0.836,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"qwen/qwen3-32b","source":"aider","metric":"polyglot_solved_count","value":90,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"qwen/qwen3-32b","source":"aider","metric":"polyglot_test_cases","value":225,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"qwen/qwen3-32b","source":"aider","metric":"polyglot_prompt_tokens","value":317591,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"qwen/qwen3-32b","source":"aider","metric":"polyglot_completion_tokens","value":120418,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"qwen/qwen3-32b","source":"aider","metric":"polyglot_seconds_per_case","value":372.2,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4.1-mini","source":"aider","metric":"polyglot_pass_rate","value":0.324,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4.1-mini","source":"aider","metric":"polyglot_run_cost_usd","value":1.99,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4.1-mini","source":"aider","metric":"polyglot_first_try_rate","value":0.111,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4.1-mini","source":"aider","metric":"polyglot_well_formed_rate","value":0.924,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4.1-mini","source":"aider","metric":"polyglot_solved_count","value":73,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4.1-mini","source":"aider","metric":"polyglot_test_cases","value":225,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4.1-mini","source":"aider","metric":"polyglot_seconds_per_case","value":19.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4o-2024-08-06","source":"aider","metric":"polyglot_pass_rate","value":0.231,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4o-2024-08-06","source":"aider","metric":"polyglot_run_cost_usd","value":7.03,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4o-2024-08-06","source":"aider","metric":"polyglot_first_try_rate","value":0.049,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4o-2024-08-06","source":"aider","metric":"polyglot_well_formed_rate","value":0.942,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4o-2024-08-06","source":"aider","metric":"polyglot_solved_count","value":52,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4o-2024-08-06","source":"aider","metric":"polyglot_test_cases","value":225,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4o-2024-08-06","source":"aider","metric":"polyglot_seconds_per_case","value":16,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4o-2024-11-20","source":"aider","metric":"polyglot_pass_rate","value":0.182,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4o-2024-11-20","source":"aider","metric":"polyglot_run_cost_usd","value":6.74,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4o-2024-11-20","source":"aider","metric":"polyglot_first_try_rate","value":0.049,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4o-2024-11-20","source":"aider","metric":"polyglot_well_formed_rate","value":0.951,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4o-2024-11-20","source":"aider","metric":"polyglot_solved_count","value":41,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4o-2024-11-20","source":"aider","metric":"polyglot_test_cases","value":225,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4o-2024-11-20","source":"aider","metric":"polyglot_seconds_per_case","value":12.1,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"aider","metric":"polyglot_pass_rate","value":0.16399999999999998,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"aider","metric":"polyglot_first_try_rate","value":0.049,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"aider","metric":"polyglot_well_formed_rate","value":0.996,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"aider","metric":"polyglot_solved_count","value":37,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"aider","metric":"polyglot_test_cases","value":225,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"aider","metric":"polyglot_seconds_per_case","value":42,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"meta-llama/llama-4-maverick","source":"aider","metric":"polyglot_pass_rate","value":0.156,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"meta-llama/llama-4-maverick","source":"aider","metric":"polyglot_first_try_rate","value":0.044,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"meta-llama/llama-4-maverick","source":"aider","metric":"polyglot_well_formed_rate","value":0.991,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"meta-llama/llama-4-maverick","source":"aider","metric":"polyglot_solved_count","value":35,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"meta-llama/llama-4-maverick","source":"aider","metric":"polyglot_test_cases","value":225,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"meta-llama/llama-4-maverick","source":"aider","metric":"polyglot_seconds_per_case","value":20.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4.1-nano","source":"aider","metric":"polyglot_pass_rate","value":0.08900000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4.1-nano","source":"aider","metric":"polyglot_run_cost_usd","value":0.43,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4.1-nano","source":"aider","metric":"polyglot_first_try_rate","value":0.031,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4.1-nano","source":"aider","metric":"polyglot_well_formed_rate","value":0.942,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4.1-nano","source":"aider","metric":"polyglot_solved_count","value":20,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4.1-nano","source":"aider","metric":"polyglot_test_cases","value":225,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4.1-nano","source":"aider","metric":"polyglot_seconds_per_case","value":12,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"google/gemma-3-27b-it","source":"aider","metric":"polyglot_pass_rate","value":0.049,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"google/gemma-3-27b-it","source":"aider","metric":"polyglot_first_try_rate","value":0.018,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"google/gemma-3-27b-it","source":"aider","metric":"polyglot_well_formed_rate","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"google/gemma-3-27b-it","source":"aider","metric":"polyglot_solved_count","value":11,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"google/gemma-3-27b-it","source":"aider","metric":"polyglot_test_cases","value":225,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"google/gemma-3-27b-it","source":"aider","metric":"polyglot_seconds_per_case","value":79.7,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"aider","metric":"polyglot_pass_rate","value":0.036000000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"aider","metric":"polyglot_run_cost_usd","value":0.32,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"aider","metric":"polyglot_first_try_rate","value":0.009,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"aider","metric":"polyglot_well_formed_rate","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"aider","metric":"polyglot_solved_count","value":8,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"aider","metric":"polyglot_test_cases","value":225,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"aider","metric":"polyglot_seconds_per_case","value":17.3,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://aider.chat/docs/leaderboards/"},{"modelId":"anthropic/claude-fable-5","source":"ale-bench","metric":"ale_bench_performance","value":2041.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"claude-fable-5-high"},{"modelId":"anthropic/claude-fable-5","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":2.108822,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"claude-fable-5-high"},{"modelId":"anthropic/claude-fable-5","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":45507,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"claude-fable-5-high"},{"modelId":"anthropic/claude-fable-5.1","source":"ale-bench","metric":"ale_bench_performance","value":2143.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"claude-fable-5.1-high"},{"modelId":"anthropic/claude-fable-5.1","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":2.294856,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"claude-fable-5.1-high"},{"modelId":"anthropic/claude-fable-5.1","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":49229,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"claude-fable-5.1-high"},{"modelId":"anthropic/claude-opus-5","source":"ale-bench","metric":"ale_bench_performance","value":2164.57,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"claude-opus-5-high"},{"modelId":"anthropic/claude-opus-5","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":1.890512,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"claude-opus-5-high"},{"modelId":"anthropic/claude-opus-5","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":78951,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"claude-opus-5-high"},{"modelId":"anthropic/claude-opus-5.5","source":"ale-bench","metric":"ale_bench_performance","value":2147.38,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"claude-opus-5.5-high"},{"modelId":"anthropic/claude-opus-5.5","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.271178,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"claude-opus-5.5-high"},{"modelId":"anthropic/claude-opus-5.5","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":16891,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"claude-opus-5.5-high"},{"modelId":"anthropic/claude-sonnet-5","source":"ale-bench","metric":"ale_bench_performance","value":1463.13,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"claude-sonnet-5-high"},{"modelId":"anthropic/claude-sonnet-5","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.96046,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"claude-sonnet-5-high"},{"modelId":"anthropic/claude-sonnet-5","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":67361,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"claude-sonnet-5-high"},{"modelId":"anthropic/claude-sonnet-5.5","source":"ale-bench","metric":"ale_bench_performance","value":1819.13,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"claude-sonnet-5.5-high"},{"modelId":"anthropic/claude-sonnet-5.5","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.110921,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"claude-sonnet-5.5-high"},{"modelId":"anthropic/claude-sonnet-5.5","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":14424,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"claude-sonnet-5.5-high"},{"modelId":"mistralai/codestral-2508","source":"ale-bench","metric":"ale_bench_performance","value":137.78,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"codestral-2508"},{"modelId":"mistralai/codestral-2508","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.00278,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"codestral-2508"},{"modelId":"mistralai/codestral-2508","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":5169,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"codestral-2508"},{"modelId":"deepseek/deepseek-r1-0528","source":"ale-bench","metric":"ale_bench_performance","value":804.13,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"deepseek-r1-0528"},{"modelId":"deepseek/deepseek-r1-0528","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.043794,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"deepseek-r1-0528"},{"modelId":"deepseek/deepseek-r1-0528","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":23890,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"deepseek-r1-0528"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"ale-bench","metric":"ale_bench_performance","value":745.18,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"deepseek-v3.1-terminus"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.01883,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"deepseek-v3.1-terminus"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":20988,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"deepseek-v3.1-terminus"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"ale-bench","metric":"ale_bench_performance","value":1306.08,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"deepseek-v4-flash-0731-max"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.019526,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"deepseek-v4-flash-0731-max"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":71432,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"deepseek-v4-flash-0731-max"},{"modelId":"deepseek/deepseek-v4-flash","source":"ale-bench","metric":"ale_bench_performance","value":678.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"deepseek-v4-flash-high"},{"modelId":"deepseek/deepseek-v4-flash","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.005179,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"deepseek-v4-flash-high"},{"modelId":"deepseek/deepseek-v4-flash","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":21119,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"deepseek-v4-flash-high"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"ale-bench","metric":"ale_bench_performance","value":1403.15,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"deepseek-v4-pro-0813-max"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.072764,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"deepseek-v4-pro-0813-max"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":85272,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"deepseek-v4-pro-0813-max"},{"modelId":"deepseek/deepseek-v4-pro","source":"ale-bench","metric":"ale_bench_performance","value":1006.08,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"deepseek-v4-pro-high"},{"modelId":"deepseek/deepseek-v4-pro","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.148062,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"deepseek-v4-pro-high"},{"modelId":"deepseek/deepseek-v4-pro","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":45318,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"deepseek-v4-pro-high"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"ale-bench","metric":"ale_bench_performance","value":1622,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"deepseek-v4.1-flash-1017-max"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.100044,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"deepseek-v4.1-flash-1017-max"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":85663,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"deepseek-v4.1-flash-1017-max"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"ale-bench","metric":"ale_bench_performance","value":1092.35,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"deepseek-v4.1-flash-max"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.081663,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"deepseek-v4.1-flash-max"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":70295,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"deepseek-v4.1-flash-max"},{"modelId":"google/gemini-3-flash-preview","source":"ale-bench","metric":"ale_bench_performance","value":1367.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gemini-3-flash-preview-high"},{"modelId":"google/gemini-3-flash-preview","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.091067,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gemini-3-flash-preview-high"},{"modelId":"google/gemini-3-flash-preview","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":33248,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gemini-3-flash-preview-high"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"ale-bench","metric":"ale_bench_performance","value":797.73,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gemini-3.1-flash-lite-preview-high"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.025178,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gemini-3.1-flash-lite-preview-high"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":19502,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gemini-3.1-flash-lite-preview-high"},{"modelId":"google/gemini-3.1-pro-preview","source":"ale-bench","metric":"ale_bench_performance","value":1160.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gemini-3.1-pro-preview-high"},{"modelId":"google/gemini-3.1-pro-preview","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.388403,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gemini-3.1-pro-preview-high"},{"modelId":"google/gemini-3.1-pro-preview","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":35084,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gemini-3.1-pro-preview-high"},{"modelId":"google/gemini-3.5-flash","source":"ale-bench","metric":"ale_bench_performance","value":911.03,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gemini-3.5-flash-high"},{"modelId":"google/gemini-3.5-flash","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.441921,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gemini-3.5-flash-high"},{"modelId":"google/gemini-3.5-flash","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":51880,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gemini-3.5-flash-high"},{"modelId":"google/gemini-3.5-flash-lite","source":"ale-bench","metric":"ale_bench_performance","value":765.28,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gemini-3.5-flash-lite-high"},{"modelId":"google/gemini-3.5-flash-lite","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.045726,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gemini-3.5-flash-lite-high"},{"modelId":"google/gemini-3.5-flash-lite","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":21160,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gemini-3.5-flash-lite-high"},{"modelId":"google/gemini-3.6-flash","source":"ale-bench","metric":"ale_bench_performance","value":715.53,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gemini-3.6-flash-high"},{"modelId":"google/gemini-3.6-flash","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.244468,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gemini-3.6-flash-high"},{"modelId":"google/gemini-3.6-flash","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":35204,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gemini-3.6-flash-high"},{"modelId":"google/gemini-3.7-flash","source":"ale-bench","metric":"ale_bench_performance","value":904.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gemini-3.7-flash-high"},{"modelId":"google/gemini-3.7-flash","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.243628,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gemini-3.7-flash-high"},{"modelId":"google/gemini-3.7-flash","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":35110,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gemini-3.7-flash-high"},{"modelId":"google/gemini-3.8-flash","source":"ale-bench","metric":"ale_bench_performance","value":1269.72,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gemini-3.8-flash-high"},{"modelId":"google/gemini-3.8-flash","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.344275,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gemini-3.8-flash-high"},{"modelId":"google/gemini-3.8-flash","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":48512,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gemini-3.8-flash-high"},{"modelId":"google/gemini-4-argon","source":"ale-bench","metric":"ale_bench_performance","value":2100.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gemini-4-argon-high"},{"modelId":"google/gemini-4-argon","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":1.949743,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gemini-4-argon-high"},{"modelId":"google/gemini-4-argon","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":192623,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gemini-4-argon-high"},{"modelId":"google/gemma-4-26b-a4b-it","source":"ale-bench","metric":"ale_bench_performance","value":927.18,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gemma-4-26b-a4b-it"},{"modelId":"google/gemma-4-26b-a4b-it","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.009725,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gemma-4-26b-a4b-it"},{"modelId":"google/gemma-4-26b-a4b-it","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":27350,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gemma-4-26b-a4b-it"},{"modelId":"google/gemma-4-31b-it","source":"ale-bench","metric":"ale_bench_performance","value":925.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gemma-4-31b-it"},{"modelId":"google/gemma-4-31b-it","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.00475,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gemma-4-31b-it"},{"modelId":"google/gemma-4-31b-it","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":14037,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gemma-4-31b-it"},{"modelId":"z-ai/glm-4.5","source":"ale-bench","metric":"ale_bench_performance","value":344.83,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"glm-4.5"},{"modelId":"z-ai/glm-4.5","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.030077,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"glm-4.5"},{"modelId":"z-ai/glm-4.5","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":16482,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"glm-4.5"},{"modelId":"z-ai/glm-4.6","source":"ale-bench","metric":"ale_bench_performance","value":340.83,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"glm-4.6"},{"modelId":"z-ai/glm-4.6","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.018794,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"glm-4.6"},{"modelId":"z-ai/glm-4.6","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":10883,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"glm-4.6"},{"modelId":"z-ai/glm-4.7","source":"ale-bench","metric":"ale_bench_performance","value":399.48,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"glm-4.7"},{"modelId":"z-ai/glm-4.7","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.043156,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"glm-4.7"},{"modelId":"z-ai/glm-4.7","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":22000,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"glm-4.7"},{"modelId":"z-ai/glm-5-turbo","source":"ale-bench","metric":"ale_bench_performance","value":633.98,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"glm-5-turbo"},{"modelId":"z-ai/glm-5-turbo","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.109512,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"glm-5-turbo"},{"modelId":"z-ai/glm-5-turbo","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":29856,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"glm-5-turbo"},{"modelId":"z-ai/glm-5.1","source":"ale-bench","metric":"ale_bench_performance","value":887.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"glm-5.1"},{"modelId":"z-ai/glm-5.1","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.12937,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"glm-5.1"},{"modelId":"z-ai/glm-5.1","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":31928,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"glm-5.1"},{"modelId":"z-ai/glm-5.2","source":"ale-bench","metric":"ale_bench_performance","value":1046.95,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"glm-5.2-high"},{"modelId":"z-ai/glm-5.2","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.157666,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"glm-5.2-high"},{"modelId":"z-ai/glm-5.2","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":38099,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"glm-5.2-high"},{"modelId":"z-ai/glm-5.3-flash","source":"ale-bench","metric":"ale_bench_performance","value":303.55,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"glm-5.3-flash-high"},{"modelId":"z-ai/glm-5.3-flash","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.010869,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"glm-5.3-flash-high"},{"modelId":"z-ai/glm-5.3-flash","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":23975,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"glm-5.3-flash-high"},{"modelId":"z-ai/glm-5.3","source":"ale-bench","metric":"ale_bench_performance","value":1317.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"glm-5.3-high"},{"modelId":"z-ai/glm-5.3","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.284001,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"glm-5.3-high"},{"modelId":"z-ai/glm-5.3","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":67123,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"glm-5.3-high"},{"modelId":"z-ai/glm-5","source":"ale-bench","metric":"ale_bench_performance","value":765.63,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"glm-5"},{"modelId":"z-ai/glm-5","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.073284,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"glm-5"},{"modelId":"z-ai/glm-5","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":25199,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"glm-5"},{"modelId":"openai/gpt-4.1","source":"ale-bench","metric":"ale_bench_performance","value":558.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-4.1"},{"modelId":"openai/gpt-4.1","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.026917,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-4.1"},{"modelId":"openai/gpt-4.1","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":5651,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-4.1"},{"modelId":"openai/gpt-5.1-codex","source":"ale-bench","metric":"ale_bench_performance","value":1244.93,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.1-codex-high"},{"modelId":"openai/gpt-5.1-codex","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.512093,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.1-codex-high"},{"modelId":"openai/gpt-5.1-codex","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":54011,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.1-codex-high"},{"modelId":"openai/gpt-5.1-codex-max","source":"ale-bench","metric":"ale_bench_performance","value":1228.25,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.1-codex-max-xhigh"},{"modelId":"openai/gpt-5.1-codex-max","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.317487,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.1-codex-max-xhigh"},{"modelId":"openai/gpt-5.1-codex-max","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":34566,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.1-codex-max-xhigh"},{"modelId":"openai/gpt-5.2-codex","source":"ale-bench","metric":"ale_bench_performance","value":1299.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.2-codex-xhigh"},{"modelId":"openai/gpt-5.2-codex","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.587753,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.2-codex-xhigh"},{"modelId":"openai/gpt-5.2-codex","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":46134,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.2-codex-xhigh"},{"modelId":"openai/gpt-5.2","source":"ale-bench","metric":"ale_bench_performance","value":1293.55,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.2-high"},{"modelId":"openai/gpt-5.2","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.296865,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.2-high"},{"modelId":"openai/gpt-5.2","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":24031,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.2-high"},{"modelId":"openai/gpt-5.3-codex","source":"ale-bench","metric":"ale_bench_performance","value":1655.23,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.3-codex-xhigh"},{"modelId":"openai/gpt-5.3-codex","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.559265,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.3-codex-xhigh"},{"modelId":"openai/gpt-5.3-codex","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":49286,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.3-codex-xhigh"},{"modelId":"openai/gpt-5.4","source":"ale-bench","metric":"ale_bench_performance","value":1607,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.4-high"},{"modelId":"openai/gpt-5.4","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.612174,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.4-high"},{"modelId":"openai/gpt-5.4","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":45461,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.4-high"},{"modelId":"openai/gpt-5.4-mini","source":"ale-bench","metric":"ale_bench_performance","value":1188.58,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.4-mini-high"},{"modelId":"openai/gpt-5.4-mini","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.271408,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.4-mini-high"},{"modelId":"openai/gpt-5.4-mini","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":72952,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.4-mini-high"},{"modelId":"openai/gpt-5.4-nano","source":"ale-bench","metric":"ale_bench_performance","value":1004.53,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.4-nano-high"},{"modelId":"openai/gpt-5.4-nano","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.027084,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.4-nano-high"},{"modelId":"openai/gpt-5.4-nano","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":24378,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.4-nano-high"},{"modelId":"openai/gpt-5.5","source":"ale-bench","metric":"ale_bench_performance","value":1942.98,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.5-xhigh"},{"modelId":"openai/gpt-5.5","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":1.517133,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.5-xhigh"},{"modelId":"openai/gpt-5.5","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":54091,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.5-xhigh"},{"modelId":"openai/gpt-5.6-luna","source":"ale-bench","metric":"ale_bench_performance","value":1667.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.6-luna-max"},{"modelId":"openai/gpt-5.6-luna","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.359171,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.6-luna-max"},{"modelId":"openai/gpt-5.6-luna","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":85180,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.6-luna-max"},{"modelId":"openai/gpt-5.6-sol","source":"ale-bench","metric":"ale_bench_performance","value":2176.88,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.6-sol-max"},{"modelId":"openai/gpt-5.6-sol","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":1.534078,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.6-sol-max"},{"modelId":"openai/gpt-5.6-sol","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":58696,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.6-sol-max"},{"modelId":"openai/gpt-5.6-terra","source":"ale-bench","metric":"ale_bench_performance","value":1951.43,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.6-terra-max"},{"modelId":"openai/gpt-5.6-terra","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":1.254047,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.6-terra-max"},{"modelId":"openai/gpt-5.6-terra","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":86477,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5.6-terra-max"},{"modelId":"openai/gpt-5","source":"ale-bench","metric":"ale_bench_performance","value":807.65,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5"},{"modelId":"openai/gpt-5","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.043745,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5"},{"modelId":"openai/gpt-5","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":7007,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-5"},{"modelId":"openai/gpt-6-astra","source":"ale-bench","metric":"ale_bench_performance","value":2951.33,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-6-astra-max"},{"modelId":"openai/gpt-6-astra","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":2.86415,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-6-astra-max"},{"modelId":"openai/gpt-6-astra","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":60104,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-6-astra-max"},{"modelId":"openai/gpt-6-luna","source":"ale-bench","metric":"ale_bench_performance","value":1576.93,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-6-luna-xhigh"},{"modelId":"openai/gpt-6-luna","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.018045,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-6-luna-xhigh"},{"modelId":"openai/gpt-6-luna","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":38984,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-6-luna-xhigh"},{"modelId":"openai/gpt-6-sol","source":"ale-bench","metric":"ale_bench_performance","value":2462,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-6-sol-max"},{"modelId":"openai/gpt-6-sol","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.843984,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-6-sol-max"},{"modelId":"openai/gpt-6-sol","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":87318,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-6-sol-max"},{"modelId":"openai/gpt-6.1-sol","source":"ale-bench","metric":"ale_bench_performance","value":2743.75,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-6.1-sol-max"},{"modelId":"openai/gpt-6.1-sol","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.596828,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-6.1-sol-max"},{"modelId":"openai/gpt-6.1-sol","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":62549,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-6.1-sol-max"},{"modelId":"openai/gpt-oss-120b","source":"ale-bench","metric":"ale_bench_performance","value":575.63,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-oss-120b"},{"modelId":"openai/gpt-oss-120b","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.001303,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-oss-120b"},{"modelId":"openai/gpt-oss-120b","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":5041,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-oss-120b"},{"modelId":"openai/gpt-oss-20b","source":"ale-bench","metric":"ale_bench_performance","value":566.05,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-oss-20b"},{"modelId":"openai/gpt-oss-20b","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.000717,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-oss-20b"},{"modelId":"openai/gpt-oss-20b","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":5951,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"gpt-oss-20b"},{"modelId":"x-ai/grok-4.3","source":"ale-bench","metric":"ale_bench_performance","value":944.18,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"grok-4.3"},{"modelId":"x-ai/grok-4.3","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.055799,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"grok-4.3"},{"modelId":"x-ai/grok-4.3","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":24066,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"grok-4.3"},{"modelId":"x-ai/grok-4.5","source":"ale-bench","metric":"ale_bench_performance","value":1309.28,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"grok-4.5-high"},{"modelId":"x-ai/grok-4.5","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.176767,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"grok-4.5-high"},{"modelId":"x-ai/grok-4.5","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":32347,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"grok-4.5-high"},{"modelId":"x-ai/grok-4.6","source":"ale-bench","metric":"ale_bench_performance","value":1508.08,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"grok-4.6-xhigh"},{"modelId":"x-ai/grok-4.6","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.24005,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"grok-4.6-xhigh"},{"modelId":"x-ai/grok-4.6","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":42843,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"grok-4.6-xhigh"},{"modelId":"tencent/hy3","source":"ale-bench","metric":"ale_bench_performance","value":838.65,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"hy3-high"},{"modelId":"tencent/hy3","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.026263,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"hy3-high"},{"modelId":"tencent/hy3","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":45985,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"hy3-high"},{"modelId":"thinkingmachines/inkling","source":"ale-bench","metric":"ale_bench_performance","value":946,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"inkling-max"},{"modelId":"thinkingmachines/inkling","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.202548,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"inkling-max"},{"modelId":"thinkingmachines/inkling","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":55717,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"inkling-max"},{"modelId":"moonshotai/kimi-k2-0905","source":"ale-bench","metric":"ale_bench_performance","value":267.13,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"kimi-k2-0905"},{"modelId":"moonshotai/kimi-k2-0905","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.008051,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"kimi-k2-0905"},{"modelId":"moonshotai/kimi-k2-0905","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":5444,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"kimi-k2-0905"},{"modelId":"moonshotai/kimi-k2-thinking","source":"ale-bench","metric":"ale_bench_performance","value":597.5,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"kimi-k2-thinking"},{"modelId":"moonshotai/kimi-k2-thinking","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.087819,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"kimi-k2-thinking"},{"modelId":"moonshotai/kimi-k2-thinking","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":51357,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"kimi-k2-thinking"},{"modelId":"moonshotai/kimi-k2.5","source":"ale-bench","metric":"ale_bench_performance","value":821.65,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"kimi-k2.5"},{"modelId":"moonshotai/kimi-k2.5","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.047458,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"kimi-k2.5"},{"modelId":"moonshotai/kimi-k2.5","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":18681,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"kimi-k2.5"},{"modelId":"moonshotai/kimi-k2.6","source":"ale-bench","metric":"ale_bench_performance","value":1092.68,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"kimi-k2.6"},{"modelId":"moonshotai/kimi-k2.6","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.196861,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"kimi-k2.6"},{"modelId":"moonshotai/kimi-k2.6","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":51914,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"kimi-k2.6"},{"modelId":"moonshotai/kimi-k2.7-code","source":"ale-bench","metric":"ale_bench_performance","value":886.23,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"kimi-k2.7-code"},{"modelId":"moonshotai/kimi-k2.7-code","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.184743,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"kimi-k2.7-code"},{"modelId":"moonshotai/kimi-k2.7-code","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":48433,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"kimi-k2.7-code"},{"modelId":"moonshotai/kimi-k3","source":"ale-bench","metric":"ale_bench_performance","value":1524.48,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"kimi-k3-max"},{"modelId":"moonshotai/kimi-k3","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":1.281554,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"kimi-k3-max"},{"modelId":"moonshotai/kimi-k3","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":88294,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"kimi-k3-max"},{"modelId":"meta-llama/llama-4-maverick","source":"ale-bench","metric":"ale_bench_performance","value":172.98,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"llama-4-maverick"},{"modelId":"meta-llama/llama-4-maverick","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.001369,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"llama-4-maverick"},{"modelId":"meta-llama/llama-4-maverick","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":4326,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"llama-4-maverick"},{"modelId":"meituan/longcat-2.0","source":"ale-bench","metric":"ale_bench_performance","value":793.45,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"longcat-2.0"},{"modelId":"meituan/longcat-2.0","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.035933,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"longcat-2.0"},{"modelId":"meituan/longcat-2.0","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":32768,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"longcat-2.0"},{"modelId":"inception/mercury-2.5","source":"ale-bench","metric":"ale_bench_performance","value":301.65,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"mercury-2.5-high"},{"modelId":"inception/mercury-2.5","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.006234,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"mercury-2.5-high"},{"modelId":"inception/mercury-2.5","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":10710,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"mercury-2.5-high"},{"modelId":"inception/mercury-2","source":"ale-bench","metric":"ale_bench_performance","value":785.58,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"mercury-2"},{"modelId":"inception/mercury-2","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.007498,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"mercury-2"},{"modelId":"inception/mercury-2","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":12149,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"mercury-2"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"ale-bench","metric":"ale_bench_performance","value":899.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"mimo-v2.5-pro"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.102977,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"mimo-v2.5-pro"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":37165,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"mimo-v2.5-pro"},{"modelId":"xiaomi/mimo-v2.5","source":"ale-bench","metric":"ale_bench_performance","value":513.95,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"mimo-v2.5"},{"modelId":"xiaomi/mimo-v2.5","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.037558,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"mimo-v2.5"},{"modelId":"xiaomi/mimo-v2.5","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":21575,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"mimo-v2.5"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"ale-bench","metric":"ale_bench_performance","value":1244.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"mimo-v2.6-flash"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.03528,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"mimo-v2.6-flash"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":142750,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"mimo-v2.6-flash"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"ale-bench","metric":"ale_bench_performance","value":1158.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"mimo-v2.6-pro"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.108379,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"mimo-v2.6-pro"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":152523,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"mimo-v2.6-pro"},{"modelId":"minimax/minimax-m2.1","source":"ale-bench","metric":"ale_bench_performance","value":623.83,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"minimax-m2.1"},{"modelId":"minimax/minimax-m2.1","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.05359,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"minimax-m2.1"},{"modelId":"minimax/minimax-m2.1","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":47888,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"minimax-m2.1"},{"modelId":"minimax/minimax-m2.5","source":"ale-bench","metric":"ale_bench_performance","value":618.17,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"minimax-m2.5"},{"modelId":"minimax/minimax-m2.5","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.036658,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"minimax-m2.5"},{"modelId":"minimax/minimax-m2.5","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":33109,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"minimax-m2.5"},{"modelId":"minimax/minimax-m2.7","source":"ale-bench","metric":"ale_bench_performance","value":599.25,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"minimax-m2.7"},{"modelId":"minimax/minimax-m2.7","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.047177,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"minimax-m2.7"},{"modelId":"minimax/minimax-m2.7","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":41912,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"minimax-m2.7"},{"modelId":"minimax/minimax-m3","source":"ale-bench","metric":"ale_bench_performance","value":640.03,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"minimax-m3"},{"modelId":"minimax/minimax-m3","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.111764,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"minimax-m3"},{"modelId":"minimax/minimax-m3","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":55120,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"minimax-m3"},{"modelId":"mistralai/mistral-large-2512","source":"ale-bench","metric":"ale_bench_performance","value":264.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"mistral-large-3-2512"},{"modelId":"mistralai/mistral-large-2512","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.005104,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"mistral-large-3-2512"},{"modelId":"mistralai/mistral-large-2512","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":5482,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"mistral-large-3-2512"},{"modelId":"mistralai/mistral-large-4-0","source":"ale-bench","metric":"ale_bench_performance","value":1213.15,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"mistral-large-4"},{"modelId":"mistralai/mistral-large-4-0","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.456946,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"mistral-large-4"},{"modelId":"mistralai/mistral-large-4-0","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":121609,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"mistral-large-4"},{"modelId":"mistralai/mistral-medium-3.1","source":"ale-bench","metric":"ale_bench_performance","value":210.18,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"mistral-medium-3.1"},{"modelId":"mistralai/mistral-medium-3.1","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.007372,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"mistral-medium-3.1"},{"modelId":"mistralai/mistral-medium-3.1","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":6182,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"mistral-medium-3.1"},{"modelId":"mistralai/mistral-medium-3-5","source":"ale-bench","metric":"ale_bench_performance","value":763.98,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"mistral-medium-3.5"},{"modelId":"mistralai/mistral-medium-3-5","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.272986,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"mistral-medium-3.5"},{"modelId":"mistralai/mistral-medium-3-5","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":38906,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"mistral-medium-3.5"},{"modelId":"mistralai/mistral-small-2603","source":"ale-bench","metric":"ale_bench_performance","value":497.63,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"mistral-small-4"},{"modelId":"mistralai/mistral-small-2603","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.015587,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"mistral-small-4"},{"modelId":"mistralai/mistral-small-2603","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":28560,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"mistral-small-4"},{"modelId":"meta/muse-glimmer-30b","source":"ale-bench","metric":"ale_bench_performance","value":962.45,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"muse-glimmer-30b-high"},{"modelId":"meta/muse-glimmer-30b","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.029179,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"muse-glimmer-30b-high"},{"modelId":"meta/muse-glimmer-30b","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":22926,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"muse-glimmer-30b-high"},{"modelId":"meta/muse-spark-1.3","source":"ale-bench","metric":"ale_bench_performance","value":1688.35,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"muse-spark-1.3-xhigh"},{"modelId":"meta/muse-spark-1.3","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.220853,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"muse-spark-1.3-xhigh"},{"modelId":"meta/muse-spark-1.3","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":68223,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"muse-spark-1.3-xhigh"},{"modelId":"meta/muse-spark-open","source":"ale-bench","metric":"ale_bench_performance","value":1590.13,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"muse-spark-open-xhigh"},{"modelId":"meta/muse-spark-open","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.325474,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"muse-spark-open-xhigh"},{"modelId":"meta/muse-spark-open","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":99073,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"muse-spark-open-xhigh"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"ale-bench","metric":"ale_bench_performance","value":213.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"nemotron-3-super"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.008207,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"nemotron-3-super"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":18918,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"nemotron-3-super"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"ale-bench","metric":"ale_bench_performance","value":769.23,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"nemotron-3.5-lightning"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.009292,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"nemotron-3.5-lightning"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":39216,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"nemotron-3.5-lightning"},{"modelId":"amazon/nova-2-lite-v1","source":"ale-bench","metric":"ale_bench_performance","value":236.25,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"nova-2-lite-v1"},{"modelId":"amazon/nova-2-lite-v1","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.004156,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"nova-2-lite-v1"},{"modelId":"amazon/nova-2-lite-v1","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":4220,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"nova-2-lite-v1"},{"modelId":"amazon/nova-premier-v1","source":"ale-bench","metric":"ale_bench_performance","value":147.38,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"nova-premier-v1"},{"modelId":"amazon/nova-premier-v1","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.027341,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"nova-premier-v1"},{"modelId":"amazon/nova-premier-v1","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":4909,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"nova-premier-v1"},{"modelId":"openai/o3","source":"ale-bench","metric":"ale_bench_performance","value":933.55,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"o3-high"},{"modelId":"openai/o3","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.103474,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"o3-high"},{"modelId":"openai/o3","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":15284,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"o3-high"},{"modelId":"openai/o4-mini-high","source":"ale-bench","metric":"ale_bench_performance","value":826.18,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"o4-mini-high"},{"modelId":"openai/o4-mini-high","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.044719,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"o4-mini-high"},{"modelId":"openai/o4-mini-high","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":12544,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"o4-mini-high"},{"modelId":"qwen/qwen3-coder","source":"ale-bench","metric":"ale_bench_performance","value":461.45,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"qwen3-coder"},{"modelId":"qwen/qwen3-coder","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.003677,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"qwen3-coder"},{"modelId":"qwen/qwen3-coder","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":5450,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"qwen3-coder"},{"modelId":"qwen/qwen3.5-27b","source":"ale-bench","metric":"ale_bench_performance","value":349.45,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"qwen3.5-27b"},{"modelId":"qwen/qwen3.5-27b","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.041945,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"qwen3.5-27b"},{"modelId":"qwen/qwen3.5-27b","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":20324,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"qwen3.5-27b"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"ale-bench","metric":"ale_bench_performance","value":221.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"qwen3.5-35b-a3b"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.03787,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"qwen3.5-35b-a3b"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":21782,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"qwen3.5-35b-a3b"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"ale-bench","metric":"ale_bench_performance","value":621.92,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"qwen3.5-397b-a17b"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.03981,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"qwen3.5-397b-a17b"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":13771,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"qwen3.5-397b-a17b"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"ale-bench","metric":"ale_bench_performance","value":265.93,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"qwen3.5-flash"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.012215,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"qwen3.5-flash"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":32977,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"qwen3.5-flash"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"ale-bench","metric":"ale_bench_performance","value":608.92,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"qwen3.5-plus"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.025738,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"qwen3.5-plus"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":13436,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"qwen3.5-plus"},{"modelId":"qwen/qwen3.6-flash","source":"ale-bench","metric":"ale_bench_performance","value":326.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"qwen3.6-flash"},{"modelId":"qwen/qwen3.6-flash","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.035628,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"qwen3.6-flash"},{"modelId":"qwen/qwen3.6-flash","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":26463,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"qwen3.6-flash"},{"modelId":"qwen/qwen3.6-plus","source":"ale-bench","metric":"ale_bench_performance","value":670.15,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"qwen3.6-plus"},{"modelId":"qwen/qwen3.6-plus","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.057069,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"qwen3.6-plus"},{"modelId":"qwen/qwen3.6-plus","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":21734,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"qwen3.6-plus"},{"modelId":"qwen/qwen3.7-flash","source":"ale-bench","metric":"ale_bench_performance","value":420.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"qwen3.7-flash"},{"modelId":"qwen/qwen3.7-flash","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.003541,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"qwen3.7-flash"},{"modelId":"qwen/qwen3.7-flash","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":29885,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"qwen3.7-flash"},{"modelId":"qwen/qwen3.7-max","source":"ale-bench","metric":"ale_bench_performance","value":1189.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"qwen3.7-max"},{"modelId":"qwen/qwen3.7-max","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.3845,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"qwen3.7-max"},{"modelId":"qwen/qwen3.7-max","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":53436,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"qwen3.7-max"},{"modelId":"upstage/solar-pro4","source":"ale-bench","metric":"ale_bench_performance","value":179.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"solar-pro4-max"},{"modelId":"upstage/solar-pro4","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.038912,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"solar-pro4-max"},{"modelId":"upstage/solar-pro4","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":34802,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"solar-pro4-max"},{"modelId":"stepfun/step-3.7-flash","source":"ale-bench","metric":"ale_bench_performance","value":694.13,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"step-3.7-flash-medium"},{"modelId":"stepfun/step-3.7-flash","source":"ale-bench","metric":"ale_bench_cost_per_problem_usd","value":0.032705,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"step-3.7-flash-medium"},{"modelId":"stepfun/step-3.7-flash","source":"ale-bench","metric":"ale_bench_tokens_per_problem","value":31014,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","setting":"step-3.7-flash-medium"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-aime","metric":"aime_accuracy","value":0.9813,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":104.53,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/gpt-5.2","source":"vals-aime","metric":"aime_accuracy","value":0.9688,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/gpt-5.2","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":120,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/gpt-5.4","source":"vals-aime","metric":"aime_accuracy","value":0.9667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/gpt-5.4","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":121,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"x-ai/grok-4.20","source":"vals-aime","metric":"aime_accuracy","value":0.9645999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"x-ai/grok-4.20","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":106.8,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-aime","metric":"aime_accuracy","value":0.9625,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":182,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"google/gemini-3-flash-preview","source":"vals-aime","metric":"aime_accuracy","value":0.9562999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"google/gemini-3-flash-preview","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":84.01,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"anthropic/claude-opus-4.6","source":"vals-aime","metric":"aime_accuracy","value":0.9562999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"anthropic/claude-opus-4.6","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":296,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/gpt-5.4-mini","source":"vals-aime","metric":"aime_accuracy","value":0.9562999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/gpt-5.4-mini","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":300,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-aime","metric":"aime_accuracy","value":0.9562999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":323,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-aime","metric":"aime_accuracy","value":0.9542,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":212,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"qwen/qwen3.6-plus","source":"vals-aime","metric":"aime_accuracy","value":0.9458,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"qwen/qwen3.6-plus","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":516,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/gpt-5","source":"vals-aime","metric":"aime_accuracy","value":0.9337000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/gpt-5","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":292,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/gpt-5.1","source":"vals-aime","metric":"aime_accuracy","value":0.9333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/gpt-5.1","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":164,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"z-ai/glm-4.7","source":"vals-aime","metric":"aime_accuracy","value":0.9333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"z-ai/glm-4.7","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":529,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"z-ai/glm-4.6","source":"vals-aime","metric":"aime_accuracy","value":0.9270999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"z-ai/glm-4.6","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":700,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/gpt-oss-120b","source":"vals-aime","metric":"aime_accuracy","value":0.9259999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/gpt-oss-120b","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":157,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"vals-aime","metric":"aime_accuracy","value":0.925,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":240,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-aime","metric":"aime_accuracy","value":0.9229,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":328,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"z-ai/glm-5.1","source":"vals-aime","metric":"aime_accuracy","value":0.9188,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"z-ai/glm-5.1","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":375,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"z-ai/glm-5","source":"vals-aime","metric":"aime_accuracy","value":0.9167000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"z-ai/glm-5","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":459,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/gpt-5-mini","source":"vals-aime","metric":"aime_accuracy","value":0.9146,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/gpt-5-mini","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":105.53,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"minimax/minimax-m2.7","source":"vals-aime","metric":"aime_accuracy","value":0.9104000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"minimax/minimax-m2.7","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":237,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/gpt-5.4-nano","source":"vals-aime","metric":"aime_accuracy","value":0.8875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/gpt-5.4-nano","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":65.88,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"minimax/minimax-m2.5","source":"vals-aime","metric":"aime_accuracy","value":0.8875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"minimax/minimax-m2.5","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":373,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-aime","metric":"aime_accuracy","value":0.8819,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":218,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"z-ai/glm-4.5","source":"vals-aime","metric":"aime_accuracy","value":0.8667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"z-ai/glm-4.5","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":333,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/o3-mini","source":"vals-aime","metric":"aime_accuracy","value":0.8645999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/o3-mini","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":155,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"vals-aime","metric":"aime_accuracy","value":0.8604,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":214,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/gpt-oss-20b","source":"vals-aime","metric":"aime_accuracy","value":0.8604,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/gpt-oss-20b","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":245,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"moonshotai/kimi-k2-thinking","source":"vals-aime","metric":"aime_accuracy","value":0.8542000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"moonshotai/kimi-k2-thinking","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":925,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/o3","source":"vals-aime","metric":"aime_accuracy","value":0.8528,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/o3","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":266,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"deepseek/deepseek-v3.2","source":"vals-aime","metric":"aime_accuracy","value":0.8458,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"deepseek/deepseek-v3.2","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":373,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/o4-mini","source":"vals-aime","metric":"aime_accuracy","value":0.8367,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/o4-mini","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":55.11,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-aime","metric":"aime_accuracy","value":0.8332999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":40.56,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-aime","metric":"aime_accuracy","value":0.8271,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":158,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/gpt-5-nano","source":"vals-aime","metric":"aime_accuracy","value":0.8118000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/gpt-5-nano","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":194,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"anthropic/claude-opus-4.1","source":"vals-aime","metric":"aime_accuracy","value":0.7818,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"anthropic/claude-opus-4.1","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":215,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"minimax/minimax-m2.1","source":"vals-aime","metric":"aime_accuracy","value":0.7792,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"minimax/minimax-m2.1","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":238,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/o1","source":"vals-aime","metric":"aime_accuracy","value":0.7145999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/o1","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":177,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"moonshotai/kimi-k2","source":"vals-aime","metric":"aime_accuracy","value":0.6271,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"moonshotai/kimi-k2","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":125,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"vals-aime","metric":"aime_accuracy","value":0.522,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":50.58,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/gpt-4.1-mini","source":"vals-aime","metric":"aime_accuracy","value":0.4938,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/gpt-4.1-mini","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":33.14,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"mistralai/mistral-large-2512","source":"vals-aime","metric":"aime_accuracy","value":0.4292,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"mistralai/mistral-large-2512","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":104.33,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"mistralai/mistral-medium-3.1","source":"vals-aime","metric":"aime_accuracy","value":0.4229,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"mistralai/mistral-medium-3.1","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":65.95,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"google/gemini-2.5-flash-lite","source":"vals-aime","metric":"aime_accuracy","value":0.4208,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"google/gemini-2.5-flash-lite","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":51.15,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/gpt-4.1","source":"vals-aime","metric":"aime_accuracy","value":0.3958,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/gpt-4.1","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":161,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/gpt-4.1-nano","source":"vals-aime","metric":"aime_accuracy","value":0.2646,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/gpt-4.1-nano","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":11.91,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"meta-llama/llama-4-maverick","source":"vals-aime","metric":"aime_accuracy","value":0.2521,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"meta-llama/llama-4-maverick","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":15.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"meta-llama/llama-4-scout","source":"vals-aime","metric":"aime_accuracy","value":0.18960000000000002,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"meta-llama/llama-4-scout","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":21.69,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/gpt-4o-2024-08-06","source":"vals-aime","metric":"aime_accuracy","value":0.1396,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/gpt-4o-2024-08-06","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":68.37,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"cohere/command-a","source":"vals-aime","metric":"aime_accuracy","value":0.1333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"cohere/command-a","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":23.34,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/gpt-4o-2024-11-20","source":"vals-aime","metric":"aime_accuracy","value":0.1188,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/gpt-4o-2024-11-20","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":15.78,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/gpt-4o-mini","source":"vals-aime","metric":"aime_accuracy","value":0.11460000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"openai/gpt-4o-mini","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":28.77,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"mistralai/mistral-large","source":"vals-aime","metric":"aime_accuracy","value":0.0917,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"mistralai/mistral-large","source":"vals-aime","metric":"aime_accuracy_latency_seconds","value":19.68,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/aime"},{"modelId":"anthropic/claude-opus-5.5","source":"lmarena","metric":"webdev_elo","value":1807.3060564856307,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-5.5","source":"lmarena","metric":"webdev_elo_votes","value":2925,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-5.5","source":"lmarena","metric":"webdev_elo_interval","value":13.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-astra","source":"lmarena","metric":"webdev_elo","value":1773.7830236243688,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-astra","source":"lmarena","metric":"webdev_elo_votes","value":6169,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-astra","source":"lmarena","metric":"webdev_elo_interval","value":10.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-5.5","source":"lmarena","metric":"webdev_elo","value":1768.3254240087845,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-5.5","source":"lmarena","metric":"webdev_elo_votes","value":3428,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-5.5","source":"lmarena","metric":"webdev_elo_interval","value":12.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6.1-sol","source":"lmarena","metric":"webdev_elo","value":1753.0824878249728,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6.1-sol","source":"lmarena","metric":"webdev_elo_votes","value":3072,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6.1-sol","source":"lmarena","metric":"webdev_elo_interval","value":12.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-fable-5.1","source":"lmarena","metric":"webdev_elo","value":1742.7041711201678,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-fable-5.1","source":"lmarena","metric":"webdev_elo_votes","value":7744,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-fable-5.1","source":"lmarena","metric":"webdev_elo_interval","value":8.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-5","source":"lmarena","metric":"webdev_elo","value":1688.8555367369042,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-5","source":"lmarena","metric":"webdev_elo_votes","value":18555,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-5","source":"lmarena","metric":"webdev_elo_interval","value":6.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-sol","source":"lmarena","metric":"webdev_elo","value":1683.057865543263,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-sol","source":"lmarena","metric":"webdev_elo_votes","value":4608,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-sol","source":"lmarena","metric":"webdev_elo_interval","value":10.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-4-argon","source":"lmarena","metric":"webdev_elo","value":1678.2591858987212,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-4-argon","source":"lmarena","metric":"webdev_elo_votes","value":1728,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-4-argon","source":"lmarena","metric":"webdev_elo_interval","value":15.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.8-max-0902","source":"lmarena","metric":"webdev_elo","value":1674.2869503411168,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.8-max-0902","source":"lmarena","metric":"webdev_elo_votes","value":14421,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.8-max-0902","source":"lmarena","metric":"webdev_elo_interval","value":7.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"lmarena","metric":"webdev_elo","value":1664.3348298599165,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"lmarena","metric":"webdev_elo_votes","value":2008,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"lmarena","metric":"webdev_elo_interval","value":14.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-1.3","source":"lmarena","metric":"webdev_elo","value":1659.2578923655815,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-1.3","source":"lmarena","metric":"webdev_elo_votes","value":9407,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-1.3","source":"lmarena","metric":"webdev_elo_interval","value":7.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k3","source":"lmarena","metric":"webdev_elo","value":1655.2872133251974,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k3","source":"lmarena","metric":"webdev_elo_votes","value":19592,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k3","source":"lmarena","metric":"webdev_elo_interval","value":5.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-wonder","source":"lmarena","metric":"webdev_elo","value":1651.5085784558248,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-wonder","source":"lmarena","metric":"webdev_elo_votes","value":2289,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-wonder","source":"lmarena","metric":"webdev_elo_interval","value":13.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.7","source":"lmarena","metric":"webdev_elo","value":1636.977595153854,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.7","source":"lmarena","metric":"webdev_elo_votes","value":5303,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.7","source":"lmarena","metric":"webdev_elo_interval","value":9.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"lmarena","metric":"webdev_elo","value":1633.6320142222642,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"lmarena","metric":"webdev_elo_votes","value":5293,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"lmarena","metric":"webdev_elo_interval","value":9.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"tencent/hy4-preview","source":"lmarena","metric":"webdev_elo","value":1630.9748559738932,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"tencent/hy4-preview","source":"lmarena","metric":"webdev_elo_votes","value":4798,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"tencent/hy4-preview","source":"lmarena","metric":"webdev_elo_interval","value":9.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"lmarena","metric":"webdev_elo","value":1624.9872074037098,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"lmarena","metric":"webdev_elo_votes","value":5041,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"lmarena","metric":"webdev_elo_interval","value":9.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-fable-5","source":"lmarena","metric":"webdev_elo","value":1624.279905339254,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-fable-5","source":"lmarena","metric":"webdev_elo_votes","value":15899,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-fable-5","source":"lmarena","metric":"webdev_elo_interval","value":6.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.3","source":"lmarena","metric":"webdev_elo","value":1621.1900952671192,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.3","source":"lmarena","metric":"webdev_elo_votes","value":9828,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.3","source":"lmarena","metric":"webdev_elo_interval","value":7.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"lmarena","metric":"webdev_elo","value":1618.3443578289887,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"lmarena","metric":"webdev_elo_votes","value":3528,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"lmarena","metric":"webdev_elo_interval","value":10.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.6","source":"lmarena","metric":"webdev_elo","value":1616.6399253201955,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.6","source":"lmarena","metric":"webdev_elo_votes","value":10483,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.6","source":"lmarena","metric":"webdev_elo_interval","value":7.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-sol","source":"lmarena","metric":"webdev_elo","value":1615.624243803082,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-sol","source":"lmarena","metric":"webdev_elo_votes","value":17786,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-sol","source":"lmarena","metric":"webdev_elo_interval","value":5.89,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.3-flash","source":"lmarena","metric":"webdev_elo","value":1606.8312617682348,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.3-flash","source":"lmarena","metric":"webdev_elo_votes","value":18264,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.3-flash","source":"lmarena","metric":"webdev_elo_interval","value":6.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.2","source":"lmarena","metric":"webdev_elo","value":1604.2162197370149,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.2","source":"lmarena","metric":"webdev_elo_votes","value":16657,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.2","source":"lmarena","metric":"webdev_elo_interval","value":6.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.8-27b","source":"lmarena","metric":"webdev_elo","value":1592.7620641791787,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.8-27b","source":"lmarena","metric":"webdev_elo_votes","value":16385,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.8-27b","source":"lmarena","metric":"webdev_elo_interval","value":6.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.7-flash","source":"lmarena","metric":"webdev_elo","value":1590.77741388594,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.7-flash","source":"lmarena","metric":"webdev_elo_votes","value":12636,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.7-flash","source":"lmarena","metric":"webdev_elo_interval","value":6.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-haiku-5.5","source":"lmarena","metric":"webdev_elo","value":1586.154813685055,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-haiku-5.5","source":"lmarena","metric":"webdev_elo_votes","value":3514,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-haiku-5.5","source":"lmarena","metric":"webdev_elo_interval","value":10.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.8-flash","source":"lmarena","metric":"webdev_elo","value":1584.6956846722271,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.8-flash","source":"lmarena","metric":"webdev_elo_votes","value":10851,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.8-flash","source":"lmarena","metric":"webdev_elo_interval","value":7.36,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"lmarena","metric":"webdev_elo","value":1582.3778052448145,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"lmarena","metric":"webdev_elo_votes","value":4714,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"lmarena","metric":"webdev_elo_interval","value":9.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4-flash","source":"lmarena","metric":"webdev_elo","value":1582.0962867572077,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4-flash","source":"lmarena","metric":"webdev_elo_votes","value":4947,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4-flash","source":"lmarena","metric":"webdev_elo_interval","value":9.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-luna","source":"lmarena","metric":"webdev_elo","value":1577.8007013739073,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-luna","source":"lmarena","metric":"webdev_elo_votes","value":21622,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-luna","source":"lmarena","metric":"webdev_elo_interval","value":6.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"stepfun/step-5-preview","source":"lmarena","metric":"webdev_elo","value":1566.830161228134,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"stepfun/step-5-preview","source":"lmarena","metric":"webdev_elo_votes","value":4728,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"stepfun/step-5-preview","source":"lmarena","metric":"webdev_elo_interval","value":9.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.7","source":"lmarena","metric":"webdev_elo","value":1557.8747065398977,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.7","source":"lmarena","metric":"webdev_elo_votes","value":17910,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.7","source":"lmarena","metric":"webdev_elo_interval","value":5.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.8","source":"lmarena","metric":"webdev_elo","value":1555.8818347830259,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.8","source":"lmarena","metric":"webdev_elo_votes","value":18493,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.8","source":"lmarena","metric":"webdev_elo_interval","value":5.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.5","source":"lmarena","metric":"webdev_elo","value":1552.968029443992,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.5","source":"lmarena","metric":"webdev_elo_votes","value":11082,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.5","source":"lmarena","metric":"webdev_elo_interval","value":6.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.6","source":"lmarena","metric":"webdev_elo","value":1546.555117472841,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.6","source":"lmarena","metric":"webdev_elo_votes","value":19383,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.6","source":"lmarena","metric":"webdev_elo_interval","value":5.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"mistralai/mistral-large-4-0","source":"lmarena","metric":"webdev_elo","value":1542.5238969181014,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"mistralai/mistral-large-4-0","source":"lmarena","metric":"webdev_elo_votes","value":2832,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"mistralai/mistral-large-4-0","source":"lmarena","metric":"webdev_elo_interval","value":12.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-1.1","source":"lmarena","metric":"webdev_elo","value":1542.4059821803005,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-1.1","source":"lmarena","metric":"webdev_elo_votes","value":7985,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-1.1","source":"lmarena","metric":"webdev_elo_interval","value":7.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-5","source":"lmarena","metric":"webdev_elo","value":1540.4088721789353,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-5","source":"lmarena","metric":"webdev_elo_votes","value":15755,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-5","source":"lmarena","metric":"webdev_elo_interval","value":5.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.6-flash","source":"lmarena","metric":"webdev_elo","value":1538.0531671297133,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.6-flash","source":"lmarena","metric":"webdev_elo_votes","value":8762,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.6-flash","source":"lmarena","metric":"webdev_elo_interval","value":7.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-1.2","source":"lmarena","metric":"webdev_elo","value":1533.8389450167274,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-1.2","source":"lmarena","metric":"webdev_elo_votes","value":2163,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-1.2","source":"lmarena","metric":"webdev_elo_interval","value":13.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-open","source":"lmarena","metric":"webdev_elo","value":1528.0938901467541,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-open","source":"lmarena","metric":"webdev_elo_votes","value":1380,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-open","source":"lmarena","metric":"webdev_elo_interval","value":17.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-4.6","source":"lmarena","metric":"webdev_elo","value":1522.960680340417,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-4.6","source":"lmarena","metric":"webdev_elo_votes","value":22822,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-4.6","source":"lmarena","metric":"webdev_elo_interval","value":5.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-terra","source":"lmarena","metric":"webdev_elo","value":1521.692131356515,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-terra","source":"lmarena","metric":"webdev_elo_votes","value":13919,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-terra","source":"lmarena","metric":"webdev_elo_interval","value":6.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-luna","source":"lmarena","metric":"webdev_elo","value":1518.2943646475646,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-luna","source":"lmarena","metric":"webdev_elo_votes","value":12501,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-luna","source":"lmarena","metric":"webdev_elo_interval","value":6.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.7-max","source":"lmarena","metric":"webdev_elo","value":1515.4914539445429,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.7-max","source":"lmarena","metric":"webdev_elo_votes","value":8887,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.7-max","source":"lmarena","metric":"webdev_elo_interval","value":7.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.5","source":"lmarena","metric":"webdev_elo","value":1512.5663418358338,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.5","source":"lmarena","metric":"webdev_elo_votes","value":15612,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.5","source":"lmarena","metric":"webdev_elo_interval","value":5.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.6","source":"lmarena","metric":"webdev_elo","value":1509.4775951461934,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.6","source":"lmarena","metric":"webdev_elo_votes","value":10166,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.6","source":"lmarena","metric":"webdev_elo_interval","value":7.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.1","source":"lmarena","metric":"webdev_elo","value":1508.1375693591506,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.1","source":"lmarena","metric":"webdev_elo_votes","value":10703,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.1","source":"lmarena","metric":"webdev_elo_interval","value":6.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"tencent/hy3","source":"lmarena","metric":"webdev_elo","value":1507.103908462265,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"tencent/hy3","source":"lmarena","metric":"webdev_elo_votes","value":6256,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"tencent/hy3","source":"lmarena","metric":"webdev_elo_interval","value":8.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.5-flash","source":"lmarena","metric":"webdev_elo","value":1499.4324574654108,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.5-flash","source":"lmarena","metric":"webdev_elo_votes","value":9382,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.5-flash","source":"lmarena","metric":"webdev_elo_interval","value":7.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.5","source":"lmarena","metric":"webdev_elo","value":1493.733768660129,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.5","source":"lmarena","metric":"webdev_elo_votes","value":11029,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.5","source":"lmarena","metric":"webdev_elo_interval","value":8.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m3","source":"lmarena","metric":"webdev_elo","value":1482.367033184203,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m3","source":"lmarena","metric":"webdev_elo_votes","value":19803,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m3","source":"lmarena","metric":"webdev_elo_interval","value":5.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"lmarena","metric":"webdev_elo","value":1480.2625371937938,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"lmarena","metric":"webdev_elo_votes","value":22493,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"lmarena","metric":"webdev_elo_interval","value":5.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.7-code","source":"lmarena","metric":"webdev_elo","value":1473.6297416239759,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.7-code","source":"lmarena","metric":"webdev_elo_votes","value":4962,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.7-code","source":"lmarena","metric":"webdev_elo_interval","value":9.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.4","source":"lmarena","metric":"webdev_elo","value":1463.936488966181,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.4","source":"lmarena","metric":"webdev_elo_votes","value":1350,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.4","source":"lmarena","metric":"webdev_elo_interval","value":18.89,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.6-plus","source":"lmarena","metric":"webdev_elo","value":1461.4885361118818,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.6-plus","source":"lmarena","metric":"webdev_elo_votes","value":18587,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.6-plus","source":"lmarena","metric":"webdev_elo_interval","value":5.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4-pro","source":"lmarena","metric":"webdev_elo","value":1447.3420829340432,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4-pro","source":"lmarena","metric":"webdev_elo_votes","value":13979,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4-pro","source":"lmarena","metric":"webdev_elo_interval","value":6.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.1-pro-preview","source":"lmarena","metric":"webdev_elo","value":1446.920737117052,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.1-pro-preview","source":"lmarena","metric":"webdev_elo_votes","value":24199,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.1-pro-preview","source":"lmarena","metric":"webdev_elo_interval","value":5.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.5","source":"lmarena","metric":"webdev_elo","value":1438.3183333245383,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.5","source":"lmarena","metric":"webdev_elo_votes","value":14910,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.5","source":"lmarena","metric":"webdev_elo_interval","value":6.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"reflection/beam-1.0-501b-a23b","source":"lmarena","metric":"webdev_elo","value":1436.8574799551702,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"reflection/beam-1.0-501b-a23b","source":"lmarena","metric":"webdev_elo_votes","value":2930,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"reflection/beam-1.0-501b-a23b","source":"lmarena","metric":"webdev_elo_interval","value":12.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.5","source":"lmarena","metric":"webdev_elo","value":1436.6395448331718,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.5","source":"lmarena","metric":"webdev_elo_votes","value":20091,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.5","source":"lmarena","metric":"webdev_elo_interval","value":5.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5","source":"lmarena","metric":"webdev_elo","value":1435.3879694650066,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5","source":"lmarena","metric":"webdev_elo_votes","value":7496,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5","source":"lmarena","metric":"webdev_elo_interval","value":8.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-4.7","source":"lmarena","metric":"webdev_elo","value":1435.3365216838056,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-4.7","source":"lmarena","metric":"webdev_elo_votes","value":4007,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-4.7","source":"lmarena","metric":"webdev_elo_interval","value":12.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.5-flash-lite","source":"lmarena","metric":"webdev_elo","value":1434.9148600466806,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.5-flash-lite","source":"lmarena","metric":"webdev_elo_votes","value":238,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.5-flash-lite","source":"lmarena","metric":"webdev_elo_interval","value":40.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5","source":"lmarena","metric":"webdev_elo","value":1417.5545917447607,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5","source":"lmarena","metric":"webdev_elo_votes","value":3092,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5","source":"lmarena","metric":"webdev_elo_interval","value":15.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.2","source":"lmarena","metric":"webdev_elo","value":1416.787778417848,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.2","source":"lmarena","metric":"webdev_elo_votes","value":1081,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.2","source":"lmarena","metric":"webdev_elo_interval","value":22.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"thinkingmachines/inkling","source":"lmarena","metric":"webdev_elo","value":1413.9232741030883,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"thinkingmachines/inkling","source":"lmarena","metric":"webdev_elo_votes","value":15778,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"thinkingmachines/inkling","source":"lmarena","metric":"webdev_elo_interval","value":6.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"thinkingmachines/inkling-small","source":"lmarena","metric":"webdev_elo","value":1409.3748760790254,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"thinkingmachines/inkling-small","source":"lmarena","metric":"webdev_elo_votes","value":5323,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"thinkingmachines/inkling-small","source":"lmarena","metric":"webdev_elo_interval","value":9.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.3-codex","source":"lmarena","metric":"webdev_elo","value":1406.558302135507,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.3-codex","source":"lmarena","metric":"webdev_elo_votes","value":2641,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.3-codex","source":"lmarena","metric":"webdev_elo_interval","value":13.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5v-turbo","source":"lmarena","metric":"webdev_elo","value":1401.78333311996,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5v-turbo","source":"lmarena","metric":"webdev_elo_votes","value":2403,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5v-turbo","source":"lmarena","metric":"webdev_elo_interval","value":13.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"lmarena","metric":"webdev_elo","value":1400.4186856730862,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"lmarena","metric":"webdev_elo_votes","value":21156,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"lmarena","metric":"webdev_elo_interval","value":5.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m2.7","source":"lmarena","metric":"webdev_elo","value":1398.5399632894942,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m2.7","source":"lmarena","metric":"webdev_elo_votes","value":15972,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m2.7","source":"lmarena","metric":"webdev_elo_interval","value":5.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.4-mini","source":"lmarena","metric":"webdev_elo","value":1397.4411041391807,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.4-mini","source":"lmarena","metric":"webdev_elo_votes","value":11942,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.4-mini","source":"lmarena","metric":"webdev_elo_interval","value":6.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.1","source":"lmarena","metric":"webdev_elo","value":1395.9553142105376,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.1","source":"lmarena","metric":"webdev_elo_votes","value":4910,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.1","source":"lmarena","metric":"webdev_elo_interval","value":11.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-4.5","source":"lmarena","metric":"webdev_elo","value":1393.7280737427213,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-4.5","source":"lmarena","metric":"webdev_elo_votes","value":13250,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-4.5","source":"lmarena","metric":"webdev_elo_interval","value":7.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.1","source":"lmarena","metric":"webdev_elo","value":1390.2901744440605,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.1","source":"lmarena","metric":"webdev_elo_votes","value":6927,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.1","source":"lmarena","metric":"webdev_elo_interval","value":10.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m2.5","source":"lmarena","metric":"webdev_elo","value":1386.3359205106904,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m2.5","source":"lmarena","metric":"webdev_elo_votes","value":7621,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m2.5","source":"lmarena","metric":"webdev_elo_interval","value":8.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"upstage/solar-pro4","source":"lmarena","metric":"webdev_elo","value":1370.67624103772,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"upstage/solar-pro4","source":"lmarena","metric":"webdev_elo_votes","value":4655,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"upstage/solar-pro4","source":"lmarena","metric":"webdev_elo_interval","value":10.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemma-4-31b-it","source":"lmarena","metric":"webdev_elo","value":1367.4419887077258,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemma-4-31b-it","source":"lmarena","metric":"webdev_elo_votes","value":14666,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemma-4-31b-it","source":"lmarena","metric":"webdev_elo_interval","value":6.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v3.2","source":"lmarena","metric":"webdev_elo","value":1362.3917105699861,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v3.2","source":"lmarena","metric":"webdev_elo_votes","value":6914,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v3.2","source":"lmarena","metric":"webdev_elo_interval","value":9.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"lmarena","metric":"webdev_elo","value":1360.5773988157432,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"lmarena","metric":"webdev_elo_votes","value":8235,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"lmarena","metric":"webdev_elo_interval","value":7.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemma-4-26b-a4b-it","source":"lmarena","metric":"webdev_elo","value":1359.559279211161,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemma-4-26b-a4b-it","source":"lmarena","metric":"webdev_elo_votes","value":1501,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemma-4-26b-a4b-it","source":"lmarena","metric":"webdev_elo_interval","value":16.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-27b","source":"lmarena","metric":"webdev_elo","value":1358.2730831961148,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-27b","source":"lmarena","metric":"webdev_elo_votes","value":7782,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-27b","source":"lmarena","metric":"webdev_elo_interval","value":8.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.3","source":"lmarena","metric":"webdev_elo","value":1357.654383282458,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.3","source":"lmarena","metric":"webdev_elo_votes","value":14954,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.3","source":"lmarena","metric":"webdev_elo_interval","value":6.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"tencent/hy3-preview","source":"lmarena","metric":"webdev_elo","value":1356.9195723743285,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"tencent/hy3-preview","source":"lmarena","metric":"webdev_elo_votes","value":1448,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"tencent/hy3-preview","source":"lmarena","metric":"webdev_elo_interval","value":17.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-4.6","source":"lmarena","metric":"webdev_elo","value":1341.1434412091148,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-4.6","source":"lmarena","metric":"webdev_elo_votes","value":6781,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-4.6","source":"lmarena","metric":"webdev_elo_interval","value":10.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.2-codex","source":"lmarena","metric":"webdev_elo","value":1338.7964313466746,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.2-codex","source":"lmarena","metric":"webdev_elo_votes","value":6718,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.2-codex","source":"lmarena","metric":"webdev_elo_interval","value":8.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.1-codex","source":"lmarena","metric":"webdev_elo","value":1337.239346206371,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.1-codex","source":"lmarena","metric":"webdev_elo_votes","value":5007,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.1-codex","source":"lmarena","metric":"webdev_elo_interval","value":11.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-haiku-4.5","source":"lmarena","metric":"webdev_elo","value":1330.3686171459108,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-haiku-4.5","source":"lmarena","metric":"webdev_elo_votes","value":29061,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-haiku-4.5","source":"lmarena","metric":"webdev_elo_interval","value":4.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m2","source":"lmarena","metric":"webdev_elo","value":1297.0641866818335,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m2","source":"lmarena","metric":"webdev_elo_votes","value":6714,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m2","source":"lmarena","metric":"webdev_elo_interval","value":10.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3-coder","source":"lmarena","metric":"webdev_elo","value":1274.6921335886218,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3-coder","source":"lmarena","metric":"webdev_elo_votes","value":12709,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3-coder","source":"lmarena","metric":"webdev_elo_interval","value":7.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"lmarena","metric":"webdev_elo","value":1271.7152271988905,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"lmarena","metric":"webdev_elo_votes","value":3969,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"lmarena","metric":"webdev_elo_interval","value":13.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"mistralai/mistral-medium-3-5","source":"lmarena","metric":"webdev_elo","value":1264.0851717190053,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"mistralai/mistral-medium-3-5","source":"lmarena","metric":"webdev_elo_votes","value":2317,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"mistralai/mistral-medium-3-5","source":"lmarena","metric":"webdev_elo_interval","value":14.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"lmarena","metric":"webdev_elo","value":1256.554943543144,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"lmarena","metric":"webdev_elo_votes","value":14390,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"lmarena","metric":"webdev_elo_interval","value":6.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"lmarena","metric":"webdev_elo","value":1254.0503728011156,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"lmarena","metric":"webdev_elo_votes","value":1617,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"lmarena","metric":"webdev_elo_interval","value":17.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.1-codex-mini","source":"lmarena","metric":"webdev_elo","value":1243.6874600291878,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.1-codex-mini","source":"lmarena","metric":"webdev_elo_votes","value":1154,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.1-codex-mini","source":"lmarena","metric":"webdev_elo_interval","value":22.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"lmarena","metric":"webdev_elo","value":1243.6587676661763,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"lmarena","metric":"webdev_elo_votes","value":1328,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"lmarena","metric":"webdev_elo_interval","value":19.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"arcee-ai/trinity-large-thinking","source":"lmarena","metric":"webdev_elo","value":1237.8309360109668,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"arcee-ai/trinity-large-thinking","source":"lmarena","metric":"webdev_elo_votes","value":1361,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"arcee-ai/trinity-large-thinking","source":"lmarena","metric":"webdev_elo_interval","value":20.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-2.5-pro","source":"lmarena","metric":"webdev_elo","value":1226.3200378385177,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-2.5-pro","source":"lmarena","metric":"webdev_elo_votes","value":2730,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-2.5-pro","source":"lmarena","metric":"webdev_elo_interval","value":15.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"inception/mercury-2","source":"lmarena","metric":"webdev_elo","value":1170.5481847700755,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"inception/mercury-2","source":"lmarena","metric":"webdev_elo_votes","value":954,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"inception/mercury-2","source":"lmarena","metric":"webdev_elo_interval","value":24.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.6","source":"swebench","metric":"swebench_multilingual_resolved","value":0.72,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"anthropic/claude-opus-4.6","source":"swebench","metric":"swebench_multilingual_instance_cost_usd","value":0.6629735766666667,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"anthropic/claude-opus-4.5","source":"swebench","metric":"swebench_multilingual_resolved","value":0.7070000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"anthropic/claude-opus-4.5","source":"swebench","metric":"swebench_multilingual_instance_cost_usd","value":0.8335529758333333,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"z-ai/glm-5","source":"swebench","metric":"swebench_multilingual_resolved","value":0.6970000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"z-ai/glm-5","source":"swebench","metric":"swebench_multilingual_instance_cost_usd","value":0.6424743668666667,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"minimax/minimax-m2.5","source":"swebench","metric":"swebench_multilingual_resolved","value":0.6829999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"minimax/minimax-m2.5","source":"swebench","metric":"swebench_multilingual_instance_cost_usd","value":0.10121049956228956,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"moonshotai/kimi-k2.5","source":"swebench","metric":"swebench_multilingual_resolved","value":0.6729999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"moonshotai/kimi-k2.5","source":"swebench","metric":"swebench_multilingual_instance_cost_usd","value":0.6928368501333334,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"anthropic/claude-sonnet-4.5","source":"swebench","metric":"swebench_multilingual_resolved","value":0.67,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"anthropic/claude-sonnet-4.5","source":"swebench","metric":"swebench_multilingual_instance_cost_usd","value":0.669532236,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/gpt-5.2","source":"swebench","metric":"swebench_multilingual_resolved","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/gpt-5.2","source":"swebench","metric":"swebench_multilingual_instance_cost_usd","value":0.5364109905,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/gpt-5.2-codex","source":"swebench","metric":"swebench_multilingual_resolved","value":0.6629999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/gpt-5.2-codex","source":"swebench","metric":"swebench_multilingual_instance_cost_usd","value":0.6621715578333333,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"anthropic/claude-haiku-4.5","source":"swebench","metric":"swebench_multilingual_resolved","value":0.647,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"anthropic/claude-haiku-4.5","source":"swebench","metric":"swebench_multilingual_instance_cost_usd","value":0.3794902823333333,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"deepseek/deepseek-v3.2","source":"swebench","metric":"swebench_multilingual_resolved","value":0.59,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"deepseek/deepseek-v3.2","source":"swebench","metric":"swebench_multilingual_instance_cost_usd","value":0.3838255249,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/gpt-5-mini","source":"swebench","metric":"swebench_multilingual_resolved","value":0.397,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/gpt-5-mini","source":"swebench","metric":"swebench_multilingual_instance_cost_usd","value":0.051632880333333325,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"anthropic/claude-opus-4.5","source":"swebench","metric":"swebench_full_resolved","value":0.5262,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/gpt-4o","source":"swebench","metric":"swebench_full_resolved","value":0.1883,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/gpt-4","source":"swebench","metric":"swebench_full_resolved","value":0.1247,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"anthropic/claude-opus-4.5","source":"swebench","metric":"swebench_resolved","value":0.792,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"google/gemini-3-flash-preview","source":"swebench","metric":"swebench_resolved","value":0.758,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"google/gemini-3-flash-preview","source":"swebench","metric":"swebench_instance_cost_usd","value":0.35596413079999994,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"minimax/minimax-m2.5","source":"swebench","metric":"swebench_resolved","value":0.758,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"minimax/minimax-m2.5","source":"swebench","metric":"swebench_instance_cost_usd","value":0.073289987844,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"anthropic/claude-opus-4.6","source":"swebench","metric":"swebench_resolved","value":0.7559999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"anthropic/claude-opus-4.6","source":"swebench","metric":"swebench_instance_cost_usd","value":0.5515226445,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"anthropic/claude-sonnet-4.5","source":"swebench","metric":"swebench_resolved","value":0.748,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/gpt-5","source":"swebench","metric":"swebench_resolved","value":0.7440000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"z-ai/glm-5","source":"swebench","metric":"swebench_resolved","value":0.728,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"z-ai/glm-5","source":"swebench","metric":"swebench_instance_cost_usd","value":0.53438913622,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/gpt-5.2","source":"swebench","metric":"swebench_resolved","value":0.728,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/gpt-5.2","source":"swebench","metric":"swebench_instance_cost_usd","value":0.4735670177,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/gpt-5.2-codex","source":"swebench","metric":"swebench_resolved","value":0.728,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/gpt-5.2-codex","source":"swebench","metric":"swebench_instance_cost_usd","value":0.4494238987,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"moonshotai/kimi-k2","source":"swebench","metric":"swebench_resolved","value":0.7120000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"moonshotai/kimi-k2.5","source":"swebench","metric":"swebench_resolved","value":0.708,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"moonshotai/kimi-k2.5","source":"swebench","metric":"swebench_instance_cost_usd","value":0.14655374074400002,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"deepseek/deepseek-v3.2","source":"swebench","metric":"swebench_resolved","value":0.7,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"deepseek/deepseek-v3.2","source":"swebench","metric":"swebench_instance_cost_usd","value":0.4478464965,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"qwen/qwen3-coder","source":"swebench","metric":"swebench_resolved","value":0.696,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"z-ai/glm-4.6","source":"swebench","metric":"swebench_resolved","value":0.682,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"anthropic/claude-haiku-4.5","source":"swebench","metric":"swebench_resolved","value":0.6659999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"anthropic/claude-haiku-4.5","source":"swebench","metric":"swebench_instance_cost_usd","value":0.33092443610000005,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/gpt-5.1","source":"swebench","metric":"swebench_resolved","value":0.66,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/gpt-5.1","source":"swebench","metric":"swebench_instance_cost_usd","value":0.3061554725,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/gpt-5.1-codex","source":"swebench","metric":"swebench_resolved","value":0.66,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/gpt-5.1-codex","source":"swebench","metric":"swebench_instance_cost_usd","value":0.5888823500000001,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/o4-mini","source":"swebench","metric":"swebench_resolved","value":0.6459999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"z-ai/glm-4.5","source":"swebench","metric":"swebench_resolved","value":0.642,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"moonshotai/kimi-k2-thinking","source":"swebench","metric":"swebench_resolved","value":0.634,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"moonshotai/kimi-k2-thinking","source":"swebench","metric":"swebench_instance_cost_usd","value":0.4383072354,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"minimax/minimax-m2","source":"swebench","metric":"swebench_resolved","value":0.61,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"minimax/minimax-m2","source":"swebench","metric":"swebench_instance_cost_usd","value":0.42825617729,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"qwen/qwen3-coder-30b-a3b-instruct","source":"swebench","metric":"swebench_resolved","value":0.604,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/gpt-5-mini","source":"swebench","metric":"swebench_resolved","value":0.598,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/gpt-5-mini","source":"swebench","metric":"swebench_instance_cost_usd","value":0.035477067300000005,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/o3","source":"swebench","metric":"swebench_resolved","value":0.584,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/o3","source":"swebench","metric":"swebench_instance_cost_usd","value":0.333652748,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"mistralai/devstral-2512","source":"swebench","metric":"swebench_resolved","value":0.5379999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"google/gemini-2.5-pro","source":"swebench","metric":"swebench_resolved","value":0.536,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"google/gemini-2.5-pro","source":"swebench","metric":"swebench_instance_cost_usd","value":0.28837209562500005,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"swebench","metric":"swebench_resolved","value":0.47,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/o3-mini","source":"swebench","metric":"swebench_resolved","value":0.424,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"swebench","metric":"swebench_resolved","value":0.42,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/gpt-4.1","source":"swebench","metric":"swebench_resolved","value":0.3958,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/gpt-4.1","source":"swebench","metric":"swebench_instance_cost_usd","value":0.146313124,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/gpt-4o","source":"swebench","metric":"swebench_resolved","value":0.38799999999999996,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/gpt-5-nano","source":"swebench","metric":"swebench_resolved","value":0.348,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/gpt-5-nano","source":"swebench","metric":"swebench_instance_cost_usd","value":0.03807518078,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"google/gemini-2.5-flash","source":"swebench","metric":"swebench_resolved","value":0.2873,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"google/gemini-2.5-flash","source":"swebench","metric":"swebench_instance_cost_usd","value":0.13388571835,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/gpt-oss-120b","source":"swebench","metric":"swebench_resolved","value":0.26,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/gpt-oss-120b","source":"swebench","metric":"swebench_instance_cost_usd","value":0.05711905579999999,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/gpt-4.1-mini","source":"swebench","metric":"swebench_resolved","value":0.2394,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/gpt-4.1-mini","source":"swebench","metric":"swebench_instance_cost_usd","value":0.43515415279999997,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/gpt-4","source":"swebench","metric":"swebench_resolved","value":0.22399999999999998,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"meta-llama/llama-4-maverick","source":"swebench","metric":"swebench_resolved","value":0.2104,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"meta-llama/llama-4-maverick","source":"swebench","metric":"swebench_instance_cost_usd","value":0.31370609759999996,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"meta-llama/llama-4-scout","source":"swebench","metric":"swebench_resolved","value":0.0906,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"meta-llama/llama-4-scout","source":"swebench","metric":"swebench_instance_cost_usd","value":0.115631523,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"qwen/qwen3-coder-30b-a3b-instruct","source":"swebench","metric":"swebench_lite_resolved","value":0.49670000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/gpt-4","source":"swebench","metric":"swebench_lite_resolved","value":0.3967,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/gpt-4o","source":"swebench","metric":"swebench_lite_resolved","value":0.38,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/o3-mini","source":"swebench","metric":"swebench_lite_resolved","value":0.3233,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"deepseek/deepseek-chat","source":"swebench","metric":"swebench_lite_resolved","value":0.30670000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/gpt-4o-2024-08-06","source":"swebench","metric":"swebench_lite_resolved","value":0.2167,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/o3","source":"swebench","metric":"swebench_multimodal_resolved","value":0.35979999999999995,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/o4-mini","source":"swebench","metric":"swebench_multimodal_resolved","value":0.3385,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/gpt-4.1","source":"swebench","metric":"swebench_multimodal_resolved","value":0.3114,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"openai/gpt-4o","source":"swebench","metric":"swebench_multimodal_resolved","value":0.3037,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.swebench.com/"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.9545,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":65.76,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-5.6-sol","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.9520000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-5.6-sol","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":58.3,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"x-ai/grok-4.6","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.9470000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"x-ai/grok-4.6","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":209,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"google/gemini-3.8-flash","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.9444,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"google/gemini-3.8-flash","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":20.18,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"google/gemini-3.7-flash","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.9394,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"google/gemini-3.7-flash","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":8.77,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.9369,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":267,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"google/gemini-3.6-flash","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.9343,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"google/gemini-3.6-flash","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":18.06,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"anthropic/claude-opus-5","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.9343,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"anthropic/claude-opus-5","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":39.59,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.9343,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":45.86,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"anthropic/claude-fable-5","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.9318000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"anthropic/claude-fable-5","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":99.9,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-5.5","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.9318000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-5.5","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":112.33,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"moonshotai/kimi-k3","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.9293,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"moonshotai/kimi-k3","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":122,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"x-ai/grok-4.5","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.9293,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"x-ai/grok-4.5","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":218,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"google/gemini-3.5-flash","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.9268000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"google/gemini-3.5-flash","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":27.66,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"minimax/minimax-m3","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.9268000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"minimax/minimax-m3","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":279,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.9242,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":134,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.9242,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":279,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-5.6-luna","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.9167000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-5.6-luna","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":53.52,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-5.2","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.9167000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-5.2","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":173,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-5.4","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.9167000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-5.4","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":203,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"x-ai/grok-4.3","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.9140999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"x-ai/grok-4.3","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":740,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"meta/muse-spark-1.1","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.9116,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"meta/muse-spark-1.1","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":75.2,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-5.6-terra","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.9091,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-5.6-terra","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":36.76,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"qwen/qwen3.7-max","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.9015000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"qwen/qwen3.7-max","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":127,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.9015000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":203,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.899,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":79.96,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"anthropic/claude-opus-4.6","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8965000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"anthropic/claude-opus-4.6","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":319,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8939,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":900,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8914,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":545,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":63.23,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"qwen/qwen3.8-27b","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"qwen/qwen3.8-27b","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":116.36,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"x-ai/grok-4.20","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8864,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"x-ai/grok-4.20","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":59.42,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"z-ai/glm-5.3","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8813,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"z-ai/glm-5.3","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":211,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"google/gemini-3-flash-preview","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8787999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"google/gemini-3-flash-preview","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":83.84,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8737,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":103.77,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"qwen/qwen3.6-plus","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8737,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"qwen/qwen3.6-plus","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":122,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"thinkingmachines/inkling","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8712000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"thinkingmachines/inkling","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":309,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-5.1","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8662000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-5.1","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":85.71,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"minimax/minimax-m2.7","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8662000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"minimax/minimax-m2.7","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":172,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8636,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":131,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8611,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":158,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8586,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":139,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-5","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8561,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-5","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":170,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"z-ai/glm-5.2","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8561,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"z-ai/glm-5.2","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":225,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8561,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":378,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8484999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":43.51,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"z-ai/glm-5.1","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8452,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"z-ai/glm-5.1","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":250,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/o3","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8409,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/o3","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":65.78,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8409,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":152,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8384,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":13.85,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"thinkingmachines/inkling-small","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8359000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"thinkingmachines/inkling-small","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":260,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"z-ai/glm-5","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8332999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"z-ai/glm-5","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":243,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-5.4-mini","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8308,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-5.4-mini","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":63.11,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8283,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":79.88,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8258,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":251,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"minimax/minimax-m2.5","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8207,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"minimax/minimax-m2.5","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":172,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8162999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":117.25,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8157,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":89.39,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8106,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":16.46,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-5-mini","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8029999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-5-mini","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":67.13,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"deepseek/deepseek-v3.2","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8029999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"deepseek/deepseek-v3.2","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":260,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"z-ai/glm-4.7","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.8005,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"z-ai/glm-4.7","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":211,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-oss-120b","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.7854000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-oss-120b","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":56.18,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"minimax/minimax-m2.1","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.7854000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"minimax/minimax-m2.1","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":135,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"moonshotai/kimi-k2-thinking","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.7854000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"moonshotai/kimi-k2-thinking","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":586,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-5.4-nano","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.7753,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-5.4-nano","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":29.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"anthropic/claude-opus-4.1","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.7626000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"anthropic/claude-opus-4.1","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":35.77,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/o3-mini","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.755,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/o3-mini","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":99.98,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/o4-mini","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.745,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/o4-mini","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":30,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"z-ai/glm-4.6","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.745,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"z-ai/glm-4.6","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":475,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/o1","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.7323000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/o1","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":40.18,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.7222,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":83.2,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"z-ai/glm-4.5","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.7222,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"z-ai/glm-4.5","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":704,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"moonshotai/kimi-k2","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.7145999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"moonshotai/kimi-k2","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":41.43,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"google/gemini-2.5-flash-lite","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.7020000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"google/gemini-2.5-flash-lite","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":20.61,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"meta-llama/llama-4-maverick","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.6944,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"meta-llama/llama-4-maverick","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":10.07,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-oss-20b","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.6894,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-oss-20b","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":145,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"mistralai/mistral-large-2512","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.6843,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"mistralai/mistral-large-2512","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":21.22,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-4.1-mini","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.6793,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-4.1-mini","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":9.28,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-4.1","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.654,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-4.1","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":23.14,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-5-nano","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.6338,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-5-nano","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":49.72,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.6162,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":23.48,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-4o-2024-11-20","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.5379,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-4o-2024-11-20","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":14.92,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-4.1-nano","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.5075999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-4.1-nano","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":4.19,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-4o-2024-05-13","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.5025,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-4o-2024-05-13","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":10.08,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"cohere/command-a","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.48479999999999995,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"cohere/command-a","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":11.49,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"mistralai/mistral-large","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.47729999999999995,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"mistralai/mistral-large","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":15.8,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"meta-llama/llama-4-scout","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.4697,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"meta-llama/llama-4-scout","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":12.09,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-4o-mini","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.44189999999999996,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-4o-mini","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":15.32,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.34850000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":256,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-3.5-turbo","source":"vals-gpqa","metric":"gpqa_accuracy","value":0.3056,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"openai/gpt-3.5-turbo","source":"vals-gpqa","metric":"gpqa_accuracy_latency_seconds","value":2.63,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/gpqa"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_long_agentic","value":0.8079999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":51.572789,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":313679,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0.958,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.812,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0.478,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.928,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.81,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_reasoning","value":0.917,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.460136,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_reasoning_output_tokens","value":8870,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.808,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_reasoning__spatial","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.86,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_coding","value":0.977,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":5.282366,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_coding_output_tokens","value":41078,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_coding__llm_api_integration","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_coding__agent_loop","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_coding__billing_limits","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_coding__product_ux","value":0.833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_coding__memory_tools","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_browser","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":3.746228,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_browser_output_tokens","value":18605,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_browser__data_aggregation","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_browser__sequential_planning","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_browser__structural_integrity","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_browser__constraint_adherence","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_data_analysis","value":0.8029999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":1.333143,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":25856,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.906,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.562,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":0.941,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_research","value":0.82,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":20.886018,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_research_output_tokens","value":70513,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.863,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_research__legal","value":0.935,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_research__tax_finance","value":0.754,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_research__strategy","value":0.565,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_research__science_evidence","value":0.935,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_design","value":0.8340000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":7.375544,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_design_output_tokens","value":59570,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_design__documents_docx","value":0.921,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_design__pdf","value":0.842,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5.1","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.792,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_long_agentic","value":0.532,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":59.736594,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":265052,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0.584,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.479,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0.014,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.883,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.659,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_reasoning","value":0.897,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.602396,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_reasoning_output_tokens","value":11716,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.846,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_reasoning__spatial","value":0.96,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.78,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_coding","value":0.983,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":8.927262,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_coding_output_tokens","value":49492,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_coding__llm_api_integration","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_coding__agent_loop","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_coding__billing_limits","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_coding__product_ux","value":0.833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_coding__memory_tools","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_browser","value":0.92,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":10.301584,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_browser_output_tokens","value":25561,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.714,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_browser__sequential_planning","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_browser__structural_integrity","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_browser__constraint_adherence","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_data_analysis","value":0.805,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":1.300688,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":25207,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.914,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.561,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":0.941,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_research","value":0.8690000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":17.274277,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_research_output_tokens","value":71540,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.888,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_research__legal","value":0.989,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_research__tax_finance","value":0.682,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_research__strategy","value":0.907,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_research__science_evidence","value":0.936,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_design","value":0.847,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":8.549472,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_design_output_tokens","value":63307,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_design__documents_docx","value":0.862,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_design__pdf","value":0.862,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.831,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_long_agentic","value":0.111,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":2.548517,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":77255,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.138,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.396,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_reasoning","value":0.617,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.442,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":0.585,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_reasoning__spatial","value":0.9,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.54,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_coding","value":0.48100000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":0.494024,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_coding_output_tokens","value":19224,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_coding__llm_api_integration","value":0.625,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_coding__agent_loop","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_coding__billing_limits","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_coding__product_ux","value":0.167,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_coding__memory_tools","value":0.74,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_browser","value":0.4,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":1.501848,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_browser_output_tokens","value":24460,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.143,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_browser__sequential_planning","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_browser__structural_integrity","value":0.4,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_browser__constraint_adherence","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_data_analysis","value":0.593,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.392,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.426,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":0.961,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_research","value":0.42200000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":0.432159,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_research_output_tokens","value":14045,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.435,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_research__legal","value":0.48,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_research__tax_finance","value":0.453,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_research__strategy","value":0.394,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_research__science_evidence","value":0.291,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_design","value":0.599,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":0.155804,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_design_output_tokens","value":11478,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_design__documents_docx","value":0.702,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_design__pdf","value":0.546,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-4.5","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.591,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_long_agentic","value":0.5760000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":10.361878,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":1001103,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0.708,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.438,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0.333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.628,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.727,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_reasoning","value":0.8240000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.020601,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_reasoning_output_tokens","value":40789,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.788,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":0.968,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_reasoning__spatial","value":0.88,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.66,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_coding","value":0.914,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":0.873786,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_coding_output_tokens","value":138052,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_coding__llm_api_integration","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_coding__agent_loop","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_coding__billing_limits","value":0.958,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":0.833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_coding__product_ux","value":0.778,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_coding__memory_tools","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_browser","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":0.460016,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_browser_output_tokens","value":42653,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.571,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_browser__sequential_planning","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_browser__structural_integrity","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_browser__constraint_adherence","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_data_analysis","value":0.531,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.031472,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":61936,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.164,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.448,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":0.98,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_research","value":0.8190000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":1.939923,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_research_output_tokens","value":235636,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.804,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_research__legal","value":0.851,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_research__tax_finance","value":0.731,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_research__strategy","value":0.854,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_research__science_evidence","value":0.922,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_design","value":0.831,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":0.663128,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_design_output_tokens","value":171437,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_design__documents_docx","value":0.924,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_design__pdf","value":0.873,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-haiku-5.5","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.764,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_long_agentic","value":0.483,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":51.969644,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":522691,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0.541,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.312,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0.111,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.739,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.683,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_reasoning","value":0.892,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.60573,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_reasoning_output_tokens","value":23900,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.808,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_reasoning__spatial","value":0.98,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.78,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_coding","value":0.773,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":4.151659,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_coding_output_tokens","value":55126,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_coding__llm_api_integration","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_coding__agent_loop","value":0.6,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_coding__billing_limits","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_coding__product_ux","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_coding__memory_tools","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_browser","value":0.96,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":8.87174,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_browser_output_tokens","value":52703,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.857,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_browser__sequential_planning","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_browser__structural_integrity","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_browser__constraint_adherence","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_data_analysis","value":0.66,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.645582,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":25286,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.529,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.511,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":0.941,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_research","value":0.818,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":6.235314,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_research_output_tokens","value":64378,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.867,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_research__legal","value":0.925,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_research__tax_finance","value":0.744,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_research__strategy","value":0.919,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_research__science_evidence","value":0.581,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_design","value":0.7879999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":6.450344,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_design_output_tokens","value":81857,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_design__documents_docx","value":0.81,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_design__pdf","value":0.786,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-4.8","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.781,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_long_agentic","value":0.85,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":38.008772,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":463030,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0.454,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.981,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.876,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_reasoning","value":0.922,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.252236,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_reasoning_output_tokens","value":12280,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.846,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_reasoning__spatial","value":0.98,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.86,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_coding","value":0.963,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":5.030783,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_coding_output_tokens","value":84646,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_coding__llm_api_integration","value":0.975,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_coding__agent_loop","value":0.96,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_coding__billing_limits","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_coding__product_ux","value":0.889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_coding__memory_tools","value":0.975,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_browser","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":14.669788,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_browser_output_tokens","value":34270,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.714,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_browser__sequential_planning","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":0.833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_browser__structural_integrity","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_browser__constraint_adherence","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_data_analysis","value":0.8029999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.81456,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":39924,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.906,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.523,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":0.98,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_research","value":0.85,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":8.81775,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_research_output_tokens","value":129426,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.872,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_research__legal","value":0.999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_research__tax_finance","value":0.82,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_research__strategy","value":0.875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_research__science_evidence","value":0.624,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_design","value":0.8690000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":5.748296,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_design_output_tokens","value":150005,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_design__documents_docx","value":0.903,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_design__pdf","value":0.882,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5.5","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.846,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_long_agentic","value":0.621,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":48.753172,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":384099,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0.625,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.604,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0.236,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.952,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.673,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_reasoning","value":0.912,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.168446,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_reasoning_output_tokens","value":6406,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.788,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_reasoning__spatial","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.86,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_coding","value":0.9079999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":3.921766,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_coding_output_tokens","value":35875,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_coding__llm_api_integration","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_coding__agent_loop","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_coding__billing_limits","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_coding__product_ux","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_coding__memory_tools","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_browser","value":0.84,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":2.965252,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_browser_output_tokens","value":17216,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.571,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_browser__sequential_planning","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_browser__structural_integrity","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_browser__constraint_adherence","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_data_analysis","value":0.746,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.745529,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":29014,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.776,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.52,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":0.941,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_research","value":0.889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":16.970368,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_research_output_tokens","value":76872,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.892,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_research__legal","value":0.972,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_research__tax_finance","value":0.794,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_research__strategy","value":0.906,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_research__science_evidence","value":0.912,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_design","value":0.83,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":5.452636,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_design_output_tokens","value":58259,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_design__documents_docx","value":0.841,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_design__pdf","value":0.864,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-opus-5","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.803,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_long_agentic","value":0.231,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":20.419611,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":310212,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.104,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.682,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.426,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_reasoning","value":0.8640000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.313031,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_reasoning_output_tokens","value":20620,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":0.945,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_reasoning__spatial","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.76,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_coding","value":0.6659999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":2.628662,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_coding_output_tokens","value":37618,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_coding__llm_api_integration","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_coding__agent_loop","value":0.4,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_coding__billing_limits","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_coding__product_ux","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_coding__memory_tools","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_browser","value":0.68,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":3.375256,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_browser_output_tokens","value":22502,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.571,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_browser__sequential_planning","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":0.833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_browser__structural_integrity","value":0.4,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_browser__constraint_adherence","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_data_analysis","value":0.7609999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.416882,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":27034,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.829,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.492,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":0.961,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_research","value":0.636,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":3.901773,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_research_output_tokens","value":35125,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.718,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_research__legal","value":0.771,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_research__tax_finance","value":0.602,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_research__strategy","value":0.428,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_research__science_evidence","value":0.53,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_design","value":0.718,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":2.138588,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_design_output_tokens","value":52865,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_design__documents_docx","value":0.668,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_design__pdf","value":0.7,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-4.6","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.751,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_long_agentic","value":0.7879999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":35.0115,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":773762,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.812,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0.361,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.849,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.825,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_reasoning","value":0.9159999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.209063,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_reasoning_output_tokens","value":20574,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.865,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_reasoning__spatial","value":0.98,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.82,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_coding","value":0.9470000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":4.021821,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_coding_output_tokens","value":124443,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_coding__llm_api_integration","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_coding__agent_loop","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_coding__billing_limits","value":0.833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":0.983,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_coding__product_ux","value":0.872,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_coding__memory_tools","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_browser","value":0.84,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":7.658836,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_browser_output_tokens","value":40564,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.714,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_browser__sequential_planning","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_browser__structural_integrity","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_browser__constraint_adherence","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_data_analysis","value":0.595,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.530634,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":52256,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.406,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.398,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":0.98,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_research","value":0.836,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":8.185618,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_research_output_tokens","value":239744,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.892,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_research__legal","value":0.951,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_research__tax_finance","value":0.605,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_research__strategy","value":0.826,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_research__science_evidence","value":0.948,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_design","value":0.85,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":5.016608,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_design_output_tokens","value":210867,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_design__documents_docx","value":0.941,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_design__pdf","value":0.876,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5.5","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.794,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_long_agentic","value":0.39,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":33.211139,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":554955,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0.166,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.396,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0.056,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.701,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.624,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_reasoning","value":0.887,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.255178,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_reasoning_output_tokens","value":25211,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.808,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":0.88,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_reasoning__spatial","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.86,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_coding","value":0.747,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":3.483062,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_coding_output_tokens","value":77338,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_coding__llm_api_integration","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_coding__agent_loop","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_coding__billing_limits","value":0.792,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":0.917,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_coding__product_ux","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_coding__memory_tools","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_browser","value":0.72,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":6.289836,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_browser_output_tokens","value":26428,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.714,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_browser__sequential_planning","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":0.833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_browser__structural_integrity","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_browser__constraint_adherence","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_data_analysis","value":0.7170000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.310066,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":30244,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.747,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.424,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":0.98,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_research","value":0.828,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":5.961141,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_research_output_tokens","value":85447,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.764,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_research__legal","value":0.971,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_research__tax_finance","value":0.742,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_research__strategy","value":0.87,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_research__science_evidence","value":0.892,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_design","value":0.82,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":5.472128,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_design_output_tokens","value":108233,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_design__documents_docx","value":0.792,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_design__pdf","value":0.815,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-sonnet-5","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.835,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_long_agentic","value":0.39,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":1.040689,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":357320,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0.375,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.835,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.42,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_reasoning","value":0.8540000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.084862,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_reasoning_output_tokens","value":64261,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.788,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":0.988,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_reasoning__spatial","value":0.96,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.68,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_coding","value":0.376,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":0.040134,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_coding_output_tokens","value":18084,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_coding__llm_api_integration","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_coding__agent_loop","value":0.4,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_coding__billing_limits","value":0.25,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":0.483,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_coding__product_ux","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_coding__memory_tools","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_browser","value":0.64,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":0.431712,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_browser_output_tokens","value":53627,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.714,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_browser__sequential_planning","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_browser__structural_integrity","value":0.6,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_browser__constraint_adherence","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_data_analysis","value":0.795,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.079032,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":59825,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.9,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.503,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":0.98,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_research","value":0.6920000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":0.248805,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_research_output_tokens","value":30492,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.806,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_research__legal","value":0.83,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_research__tax_finance","value":0.362,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_research__strategy","value":0.67,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_research__science_evidence","value":0.817,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_design","value":0.7070000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":0.059424,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_design_output_tokens","value":14589,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_design__documents_docx","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_design__pdf","value":0.618,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.727,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_long_agentic","value":0.509,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":1.458239,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":417570,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0.417,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.375,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0.347,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.822,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.62,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_reasoning","value":0.8909999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.024221,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_reasoning_output_tokens","value":19909,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.885,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_reasoning__spatial","value":0.98,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.7,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_coding","value":0.96,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":0.195538,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_coding_output_tokens","value":62695,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_coding__llm_api_integration","value":0.875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_coding__agent_loop","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_coding__billing_limits","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_coding__product_ux","value":0.889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_coding__memory_tools","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_browser","value":0.76,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":0.245012,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_browser_output_tokens","value":26695,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.714,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_browser__sequential_planning","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_browser__structural_integrity","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_browser__constraint_adherence","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_data_analysis","value":0.795,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.03316,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":26704,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.903,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.482,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_research","value":0.795,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":0.375391,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_research_output_tokens","value":124572,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.862,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_research__legal","value":0.837,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_research__tax_finance","value":0.6,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_research__strategy","value":0.816,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_research__science_evidence","value":0.89,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_design","value":0.8340000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":0.211988,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_design_output_tokens","value":113066,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_design__documents_docx","value":0.813,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_design__pdf","value":0.892,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.804,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_long_agentic","value":0.401,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":1.741518,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":451375,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0.208,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.417,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0.014,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.872,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.516,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_reasoning","value":0.867,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.045651,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_reasoning_output_tokens","value":37763,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.808,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_reasoning__spatial","value":0.98,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.68,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_coding","value":0.902,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":0.237714,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_coding_output_tokens","value":73074,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_coding__llm_api_integration","value":0.875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_coding__agent_loop","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_coding__billing_limits","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":0.889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_coding__product_ux","value":0.889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_coding__memory_tools","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_browser","value":0.84,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":0.348648,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_browser_output_tokens","value":42493,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.714,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_browser__sequential_planning","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_browser__structural_integrity","value":0.6,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_browser__constraint_adherence","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_data_analysis","value":0.7929999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.071106,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":58326,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.887,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.49,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_research","value":0.868,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":0.408664,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_research_output_tokens","value":142711,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.848,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_research__legal","value":0.91,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_research__tax_finance","value":0.846,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_research__strategy","value":0.855,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_research__science_evidence","value":0.906,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_design","value":0.792,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":0.174804,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_design_output_tokens","value":90915,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_design__documents_docx","value":0.749,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_design__pdf","value":0.868,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.758,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_long_agentic","value":0.28300000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":5.558494,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":205813,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.083,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.712,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.658,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_reasoning","value":0.878,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.068898,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_reasoning_output_tokens","value":18144,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.827,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":0.945,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_reasoning__spatial","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.74,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_coding","value":0.805,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":1.731707,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_coding_output_tokens","value":58180,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_coding__llm_api_integration","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_coding__agent_loop","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_coding__billing_limits","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":0.833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_coding__product_ux","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_coding__memory_tools","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_browser","value":0.56,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":1.069328,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_browser_output_tokens","value":27807,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.429,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_browser__sequential_planning","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":0.333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_browser__structural_integrity","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_browser__constraint_adherence","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_data_analysis","value":0.68,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.166657,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":43360,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.604,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.455,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":0.98,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_research","value":0.765,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":2.683627,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_research_output_tokens","value":127694,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_research__legal","value":0.897,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_research__tax_finance","value":0.636,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_research__strategy","value":0.894,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_research__science_evidence","value":0.517,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_design","value":0.732,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":0.62314,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_design_output_tokens","value":62179,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_design__documents_docx","value":0.809,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_design__pdf","value":0.761,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.7-flash","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.681,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_long_agentic","value":0.301,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":7.039017,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":284589,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0.167,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.083,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0.111,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.782,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.435,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_reasoning","value":0.893,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.147552,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_reasoning_output_tokens","value":39118,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.769,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":0.982,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_reasoning__spatial","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.82,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_coding","value":0.8220000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":2.296428,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_coding_output_tokens","value":111470,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_coding__llm_api_integration","value":0.875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_coding__agent_loop","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_coding__billing_limits","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_coding__product_ux","value":0.722,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_coding__memory_tools","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_browser","value":0.64,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":1.213092,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_browser_output_tokens","value":36860,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.429,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_browser__sequential_planning","value":0.25,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":0.833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_browser__structural_integrity","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_browser__constraint_adherence","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_data_analysis","value":0.54,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.237714,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":62326,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.206,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.453,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":0.961,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_research","value":0.7909999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":2.638055,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_research_output_tokens","value":135968,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.797,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_research__legal","value":0.867,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_research__tax_finance","value":0.723,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_research__strategy","value":0.804,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_research__science_evidence","value":0.776,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_design","value":0.727,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":0.979588,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_design_output_tokens","value":86732,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_design__documents_docx","value":0.831,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_design__pdf","value":0.778,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-3.8-flash","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.649,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_long_agentic","value":0.6990000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":13.841872,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":327753,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0.917,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0.194,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.976,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.684,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_reasoning","value":0.951,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.078061,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_reasoning_output_tokens","value":7571,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.923,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_reasoning__spatial","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.88,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_coding","value":0.897,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":5.076328,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_coding_output_tokens","value":115041,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_coding__llm_api_integration","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_coding__agent_loop","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_coding__billing_limits","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_coding__product_ux","value":0.778,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_coding__memory_tools","value":0.833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_browser","value":0.92,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":3.433868,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_browser_output_tokens","value":15322,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.857,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_browser__sequential_planning","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":0.833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_browser__structural_integrity","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_browser__constraint_adherence","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_data_analysis","value":0.852,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.284339,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":26732,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.914,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.699,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":0.941,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_research","value":0.831,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":5.955556,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_research_output_tokens","value":144282,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.77,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_research__legal","value":0.981,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_research__tax_finance","value":0.765,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_research__strategy","value":0.848,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_research__science_evidence","value":0.867,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_design","value":0.737,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":1.16044,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_design_output_tokens","value":60890,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_design__documents_docx","value":0.845,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_design__pdf","value":0.746,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemini-4-argon","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.686,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_long_agentic","value":0.133,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":0.988689,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":42056,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0.042,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.083,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.196,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.327,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_reasoning","value":0.6829999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.00377,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_reasoning_output_tokens","value":9019,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.731,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":0.36,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_reasoning__spatial","value":0.96,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.68,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_coding","value":0.49,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":0.23261,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_coding_output_tokens","value":11719,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_coding__llm_api_integration","value":0.542,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_coding__agent_loop","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_coding__billing_limits","value":0.25,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":0.639,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_coding__product_ux","value":0.333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_coding__memory_tools","value":0.679,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_browser","value":0.04,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":0.25412,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_browser_output_tokens","value":100134,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.143,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_browser__sequential_planning","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_browser__structural_integrity","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_browser__constraint_adherence","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_data_analysis","value":0.5329999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.004565,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":9487,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.136,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.463,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_research","value":0.444,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":0.038432,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_research_output_tokens","value":10393,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.493,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_research__legal","value":0.408,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_research__tax_finance","value":0.485,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_research__strategy","value":0.477,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_research__science_evidence","value":0.272,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_design","value":0.584,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":0.014792,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_design_output_tokens","value":9942,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_design__documents_docx","value":0.646,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_design__pdf","value":0.549,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"google/gemma-4-31b-it","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.581,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_long_agentic","value":0.284,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":1.628772,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":269870,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0.083,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.209,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.79,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.395,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_reasoning","value":0.7759999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.013782,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_reasoning_output_tokens","value":27228,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.731,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":0.795,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_reasoning__spatial","value":0.96,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.62,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_coding","value":0.8059999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":0.169586,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_coding_output_tokens","value":29839,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_coding__llm_api_integration","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_coding__agent_loop","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_coding__billing_limits","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":0.833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_coding__product_ux","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_coding__memory_tools","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_browser","value":0.84,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":0.176892,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_browser_output_tokens","value":17113,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.571,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_browser__sequential_planning","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_browser__structural_integrity","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_browser__constraint_adherence","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_data_analysis","value":0.764,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.024276,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":47359,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.843,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.488,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":0.961,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_research","value":0.701,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":0.18695,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_research_output_tokens","value":59511,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.721,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_research__legal","value":0.693,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_research__tax_finance","value":0.56,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_research__strategy","value":0.707,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_research__science_evidence","value":0.894,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_design","value":0.772,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":0.063408,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_design_output_tokens","value":38912,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_design__documents_docx","value":0.727,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_design__pdf","value":0.789,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3-flash","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.78,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_long_agentic","value":0.359,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":18.381939,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":443888,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0.375,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.271,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.65,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.483,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_reasoning","value":0.858,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.264766,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_reasoning_output_tokens","value":59828,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.885,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":0.888,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_reasoning__spatial","value":0.96,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.7,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_coding","value":0.828,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":2.138393,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_coding_output_tokens","value":45039,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_coding__llm_api_integration","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_coding__agent_loop","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_coding__billing_limits","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":0.833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_coding__product_ux","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_coding__memory_tools","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_browser","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_browser__data_aggregation","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_browser__sequential_planning","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_browser__structural_integrity","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_browser__constraint_adherence","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_data_analysis","value":0.7020000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.373101,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":83548,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.723,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.423,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":0.961,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_research","value":0.732,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":1.634592,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_research_output_tokens","value":78992,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.898,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_research__legal","value":0.741,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_research__tax_finance","value":0.32,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_research__strategy","value":0.932,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_research__science_evidence","value":0.816,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_design","value":0.773,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":0.955616,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_design_output_tokens","value":68015,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_design__documents_docx","value":0.828,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_design__pdf","value":0.755,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"z-ai/glm-5.3","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.761,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_long_agentic","value":0.446,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":13.851483,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":95488,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0.375,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.167,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0.222,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.814,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.688,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_reasoning","value":0.897,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.289229,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_reasoning_output_tokens","value":9457,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.846,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_reasoning__spatial","value":0.98,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.76,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_coding","value":0.851,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":4.207645,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_coding_output_tokens","value":18415,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_coding__llm_api_integration","value":0.875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_coding__agent_loop","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_coding__billing_limits","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_coding__product_ux","value":0.778,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_coding__memory_tools","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_browser","value":0.48,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":5.62,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_browser_output_tokens","value":79713,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.571,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_browser__sequential_planning","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_browser__structural_integrity","value":0.2,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_browser__constraint_adherence","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_data_analysis","value":0.816,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.4055,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":13299,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.888,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.559,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_research","value":0.616,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":17.137886,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_research_output_tokens","value":21217,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_research__legal","value":0.742,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_research__tax_finance","value":0.536,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_research__strategy","value":0.551,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_research__science_evidence","value":0.525,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_design","value":0.703,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":1.190356,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_design_output_tokens","value":17832,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_design__documents_docx","value":0.675,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_design__pdf","value":0.665,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.5","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.74,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_long_agentic","value":0.304,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":1.101161,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":234057,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0.125,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.125,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.695,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.596,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_reasoning","value":0.856,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.02769,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_reasoning_output_tokens","value":22753,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.731,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":0.935,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_reasoning__spatial","value":0.96,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_coding","value":0.736,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":1.823203,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_coding_output_tokens","value":35428,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_coding__llm_api_integration","value":0.875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_coding__agent_loop","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_coding__billing_limits","value":0.292,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_coding__product_ux","value":0.611,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_coding__memory_tools","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_browser","value":0.68,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":0.097344,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_browser_output_tokens","value":10159,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.714,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_browser__sequential_planning","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_browser__structural_integrity","value":0.4,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_browser__constraint_adherence","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_data_analysis","value":0.78,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.026746,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":21599,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.865,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.476,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_research","value":0.51,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":0.820777,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_research_output_tokens","value":69492,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.656,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_research__legal","value":0.25,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_research__tax_finance","value":0.293,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_research__strategy","value":0.836,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_research__science_evidence","value":0.553,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_design","value":0.76,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":0.08954,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_design_output_tokens","value":27152,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_design__documents_docx","value":0.774,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_design__pdf","value":0.785,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-luna","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.737,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_long_agentic","value":0.485,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":15.961511,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":164160,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0.542,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.417,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0.167,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.878,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.442,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_reasoning","value":0.917,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.191053,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_reasoning_output_tokens","value":9310,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.846,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_reasoning__spatial","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.82,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_coding","value":0.897,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":3.768831,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_coding_output_tokens","value":23972,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_coding__llm_api_integration","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_coding__agent_loop","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_coding__billing_limits","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_coding__product_ux","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_coding__memory_tools","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_browser","value":0.88,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":1.338172,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_browser_output_tokens","value":7727,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.86,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_browser__sequential_planning","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":0.83,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_browser__structural_integrity","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_browser__constraint_adherence","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_data_analysis","value":0.7979999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.238113,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":11094,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.902,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.493,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_research","value":0.545,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":14.425968,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_research_output_tokens","value":48343,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.662,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_research__legal","value":0.809,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_research__tax_finance","value":0.312,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_research__strategy","value":0.589,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_research__science_evidence","value":0.262,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_design","value":0.816,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":1.706208,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_design_output_tokens","value":25152,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_design__documents_docx","value":0.852,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_design__pdf","value":0.78,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-sol","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.824,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_long_agentic","value":0.484,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":11.756906,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":253005,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0.541,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.271,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0.111,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.791,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.687,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_reasoning","value":0.9059999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.187151,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_reasoning_output_tokens","value":15238,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.865,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_reasoning__spatial","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.76,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_coding","value":0.862,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":2.714731,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_coding_output_tokens","value":33438,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_coding__llm_api_integration","value":0.875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_coding__agent_loop","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_coding__billing_limits","value":0.792,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_coding__product_ux","value":0.722,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_coding__memory_tools","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_browser","value":0.84,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":0.847168,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_browser_output_tokens","value":11017,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.714,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_browser__sequential_planning","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":0.833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_browser__structural_integrity","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_browser__constraint_adherence","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_data_analysis","value":0.7929999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.222209,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":17623,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.877,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.502,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_research","value":0.604,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":7.718632,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_research_output_tokens","value":76949,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.578,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_research__legal","value":0.717,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_research__tax_finance","value":0.406,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_research__strategy","value":0.56,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_research__science_evidence","value":0.886,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_design","value":0.76,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":0.620068,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_design_output_tokens","value":23164,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_design__documents_docx","value":0.792,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_design__pdf","value":0.755,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-5.6-terra","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_long_agentic","value":0.8240000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":38.378918,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":210429,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0.291,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.983,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.751,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_reasoning","value":0.927,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.389842,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_reasoning_output_tokens","value":7577,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.846,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_reasoning__spatial","value":0.98,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.88,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_coding","value":0.937,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":3.315369,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_coding_output_tokens","value":13904,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_coding__llm_api_integration","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_coding__agent_loop","value":0.9,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_coding__billing_limits","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_coding__product_ux","value":0.945,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_coding__memory_tools","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_browser","value":0.84,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":5.909672,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_browser_output_tokens","value":3639,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.714,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_browser__sequential_planning","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":0.833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_browser__structural_integrity","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_browser__constraint_adherence","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_data_analysis","value":0.83,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.698902,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":13240,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.906,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.584,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_research","value":0.852,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":17.659868,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_research_output_tokens","value":33608,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_research__legal","value":0.944,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_research__tax_finance","value":0.85,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_research__strategy","value":0.871,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_research__science_evidence","value":0.84,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_design","value":0.82,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":2.87562,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_design_output_tokens","value":24627,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_design__documents_docx","value":0.847,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_design__pdf","value":0.783,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-astra","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.834,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_long_agentic","value":0.48100000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":0.967611,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":688782,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0.459,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.438,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0.153,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.678,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.644,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_reasoning","value":0.818,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.021405,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_reasoning_output_tokens","value":42629,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.731,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":0.96,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_reasoning__spatial","value":0.96,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.62,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_coding","value":0.845,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":0.095055,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_coding_output_tokens","value":75610,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_coding__llm_api_integration","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_coding__agent_loop","value":0.9,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_coding__billing_limits","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_coding__product_ux","value":0.833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_coding__memory_tools","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_browser","value":0.72,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":0.238208,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_browser_output_tokens","value":28295,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.714,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_browser__sequential_planning","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":0.833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_browser__structural_integrity","value":0.4,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_browser__constraint_adherence","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_data_analysis","value":0.7340000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.016605,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":32473,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.705,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.496,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_research","value":0.435,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":0.355345,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_research_output_tokens","value":241287,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.359,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_research__legal","value":0.734,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_research__tax_finance","value":0.143,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_research__strategy","value":0.553,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_research__science_evidence","value":0.583,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_design","value":0.825,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":0.030568,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_design_output_tokens","value":44762,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_design__documents_docx","value":0.865,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_design__pdf","value":0.789,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-luna","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.832,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_long_agentic","value":0.669,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":8.621461,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":212220,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0.833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.542,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0.389,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.852,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.705,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_reasoning","value":0.887,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.120914,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_reasoning_output_tokens","value":11871,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.846,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_reasoning__spatial","value":0.96,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.74,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_coding","value":0.9309999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":0.976879,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_coding_output_tokens","value":27853,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_coding__llm_api_integration","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_coding__agent_loop","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_coding__billing_limits","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_coding__product_ux","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_coding__memory_tools","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_browser","value":0.92,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":3.283764,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_browser_output_tokens","value":7523,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.857,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_browser__sequential_planning","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":0.833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_browser__structural_integrity","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_browser__constraint_adherence","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_data_analysis","value":0.812,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.198928,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":19154,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.895,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.54,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_research","value":0.693,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":3.505077,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_research_output_tokens","value":42995,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.838,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_research__legal","value":0.893,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_research__tax_finance","value":0.467,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_research__strategy","value":0.579,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_research__science_evidence","value":0.574,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_design","value":0.8220000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":0.425388,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_design_output_tokens","value":28387,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_design__documents_docx","value":0.894,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_design__pdf","value":0.83,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6-sol","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.787,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_long_agentic","value":0.73,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":6.487661,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":194893,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.938,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0.208,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.946,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.815,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_reasoning","value":0.9259999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.080313,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_reasoning_output_tokens","value":7811,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.865,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_reasoning__spatial","value":0.98,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.86,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_coding","value":0.96,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":0.4822,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_coding_output_tokens","value":14030,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_coding__llm_api_integration","value":0.833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_coding__agent_loop","value":0.9,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_coding__billing_limits","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_coding__product_ux","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_coding__memory_tools","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_browser","value":0.88,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":2.437332,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_browser_output_tokens","value":4431,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_browser__data_aggregation","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_browser__sequential_planning","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":0.833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_browser__structural_integrity","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_browser__constraint_adherence","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_data_analysis","value":0.8270000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.145418,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":13804,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.906,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.574,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_research","value":0.835,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":2.415191,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_research_output_tokens","value":44333,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.773,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_research__legal","value":0.998,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_research__tax_finance","value":0.818,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_research__strategy","value":0.76,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_research__science_evidence","value":0.867,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_design","value":0.821,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":0.370544,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_design_output_tokens","value":25521,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_design__documents_docx","value":0.862,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_design__pdf","value":0.791,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"openai/gpt-6.1-sol","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.823,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_long_agentic","value":0.27899999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":4.498294,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":80606,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0.125,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.676,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.624,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_reasoning","value":0.872,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.087717,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_reasoning_output_tokens","value":14539,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.827,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":0.94,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_reasoning__spatial","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.72,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_coding","value":0.943,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":0.959176,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_coding_output_tokens","value":15315,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_coding__llm_api_integration","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_coding__agent_loop","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_coding__billing_limits","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":0.944,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_coding__product_ux","value":0.944,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_coding__memory_tools","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_browser","value":0.44,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":2.917696,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_browser_output_tokens","value":12613,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.571,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_browser__sequential_planning","value":0.25,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_browser__structural_integrity","value":0.6,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_browser__constraint_adherence","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_data_analysis","value":0.73,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.113889,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":18701,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.755,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.436,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_research","value":0.8590000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":0.817873,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_research_output_tokens","value":15217,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.835,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_research__legal","value":0.895,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_research__tax_finance","value":0.835,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_research__strategy","value":0.905,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_research__science_evidence","value":0.863,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_design","value":0.7809999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":0.387728,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_design_output_tokens","value":24466,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_design__documents_docx","value":0.824,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_design__pdf","value":0.688,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.5","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.826,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_long_agentic","value":0.40700000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":10.625811,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":128260,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0.375,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.354,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0.056,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.804,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.456,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_reasoning","value":0.912,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.087257,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_reasoning_output_tokens","value":14139,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.904,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":0.965,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_reasoning__spatial","value":0.98,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_coding","value":0.8909999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":1.858379,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_coding_output_tokens","value":25609,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_coding__llm_api_integration","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_coding__agent_loop","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_coding__billing_limits","value":0.958,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_coding__product_ux","value":0.833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_coding__memory_tools","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_browser","value":0.64,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":2.921248,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_browser_output_tokens","value":16144,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.429,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_browser__sequential_planning","value":0.25,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":0.833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_browser__structural_integrity","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_browser__constraint_adherence","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_data_analysis","value":0.753,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.12299,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":19229,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.846,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.431,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":0.98,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_research","value":0.845,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":2.325464,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_research_output_tokens","value":28110,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.853,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_research__legal","value":0.885,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_research__tax_finance","value":0.799,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_research__strategy","value":0.829,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_research__science_evidence","value":0.868,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_design","value":0.7979999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":1.266572,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_design_output_tokens","value":46787,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_design__documents_docx","value":0.769,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_design__pdf","value":0.82,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.6","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.796,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_long_agentic","value":0.501,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":18.9333,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":283495,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0.056,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.793,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.617,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_reasoning","value":0.8270000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.385072,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_reasoning_output_tokens","value":63769,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.846,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":0.86,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_reasoning__spatial","value":0.94,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.66,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_coding","value":0.845,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":4.879883,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_coding_output_tokens","value":59183,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_coding__llm_api_integration","value":0.375,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_coding__agent_loop","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_coding__billing_limits","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_coding__product_ux","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_coding__memory_tools","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_browser","value":0.6,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":4.777796,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_browser_output_tokens","value":36667,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.857,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_browser__sequential_planning","value":0.25,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":0.167,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_browser__structural_integrity","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_browser__constraint_adherence","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_data_analysis","value":0.769,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.487966,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":80144,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.857,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.449,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_research","value":0.8640000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":4.577345,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_research_output_tokens","value":76863,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.839,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_research__legal","value":0.908,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_research__tax_finance","value":0.819,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_research__strategy","value":0.916,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_research__science_evidence","value":0.889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_design","value":0.78,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":3.369568,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_design_output_tokens","value":117654,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_design__documents_docx","value":0.729,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_design__pdf","value":0.801,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"x-ai/grok-4.7","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.786,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_long_agentic","value":0.141,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":12.405622,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":168123,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.38,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.349,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_reasoning","value":0.7829999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.104009,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_reasoning_output_tokens","value":25445,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.654,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":0.88,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_reasoning__spatial","value":0.94,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.66,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_coding","value":0.64,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":1.876617,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_coding_output_tokens","value":30579,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_coding__llm_api_integration","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_coding__agent_loop","value":0.6,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_coding__billing_limits","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_coding__product_ux","value":0.472,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_coding__memory_tools","value":0.679,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_browser","value":0.16,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":2.39616,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_browser_output_tokens","value":28102,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.429,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_browser__sequential_planning","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":0.167,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_browser__structural_integrity","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_browser__constraint_adherence","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_data_analysis","value":0.728,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.144635,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":34889,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.699,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.485,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_research","value":0.599,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":1.667995,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_research_output_tokens","value":34077,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.578,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_research__legal","value":0.607,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_research__tax_finance","value":0.6,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_research__strategy","value":0.649,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_research__science_evidence","value":0.589,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_design","value":0.583,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":0.286128,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_design_output_tokens","value":27035,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_design__documents_docx","value":0.725,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_design__pdf","value":0.505,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"thinkingmachines/inkling","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.575,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_long_agentic","value":0.428,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":17.990494,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":272271,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0.375,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.083,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0.069,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.864,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.768,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_reasoning","value":0.907,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.195096,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_reasoning_output_tokens","value":12770,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.827,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_reasoning__spatial","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_coding","value":0.593,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":2.061386,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_coding_output_tokens","value":18869,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_coding__llm_api_integration","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_coding__agent_loop","value":0.4,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_coding__billing_limits","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_coding__product_ux","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_coding__memory_tools","value":0.25,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_browser","value":0.16,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":0.382016,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_browser_output_tokens","value":5917,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.286,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_browser__sequential_planning","value":0.25,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_browser__structural_integrity","value":0.2,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_browser__constraint_adherence","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_data_analysis","value":0.787,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.352355,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":22775,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.898,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.484,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":0.98,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_research","value":0.79,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":2.404936,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_research_output_tokens","value":31404,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.784,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_research__legal","value":0.951,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_research__tax_finance","value":0.677,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_research__strategy","value":0.692,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_research__science_evidence","value":0.875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_design","value":0.772,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":1.00074,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_design_output_tokens","value":31713,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_design__documents_docx","value":0.814,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_design__pdf","value":0.79,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"moonshotai/kimi-k3","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.742,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_long_agentic","value":0.475,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":1.388622,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":417649,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0.292,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.438,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0.139,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.815,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.693,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_reasoning","value":0.7959999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.023732,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_reasoning_output_tokens","value":26730,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.865,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":0.72,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_reasoning__spatial","value":0.94,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.66,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_coding","value":0.815,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":0.223907,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_coding_output_tokens","value":82405,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_coding__llm_api_integration","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_coding__agent_loop","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_coding__billing_limits","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":0.9,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_coding__product_ux","value":0.722,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_coding__memory_tools","value":0.725,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_browser","value":0.88,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":0.456672,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_browser_output_tokens","value":33173,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.714,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_browser__sequential_planning","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_browser__structural_integrity","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_browser__constraint_adherence","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_data_analysis","value":0.723,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.038564,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":41652,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.705,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.483,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":0.98,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_research","value":0.767,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":0.142291,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_research_output_tokens","value":57443,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.77,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_research__legal","value":0.774,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_research__tax_finance","value":0.643,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_research__strategy","value":0.807,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_research__science_evidence","value":0.916,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_design","value":0.785,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":0.093224,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_design_output_tokens","value":58295,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_design__documents_docx","value":0.865,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_design__pdf","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.741,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_long_agentic","value":0.124,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":4.195256,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":254681,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.294,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.34,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_reasoning","value":0.745,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.019356,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_reasoning_output_tokens","value":15833,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.769,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":0.61,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_reasoning__spatial","value":0.94,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.66,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_coding","value":0.7090000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":0.455093,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_coding_output_tokens","value":38007,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_coding__llm_api_integration","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_coding__agent_loop","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_coding__billing_limits","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":0.889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_coding__product_ux","value":0.833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_coding__memory_tools","value":0.929,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_browser","value":0.08,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":0.429204,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_browser_output_tokens","value":29095,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.286,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_browser__sequential_planning","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_browser__structural_integrity","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_browser__constraint_adherence","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_data_analysis","value":0.762,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.028753,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":23291,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.846,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.458,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":0.98,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_research","value":0.68,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":0.2516,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_research_output_tokens","value":34479,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.737,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_research__legal","value":0.636,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_research__tax_finance","value":0.627,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_research__strategy","value":0.769,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_research__science_evidence","value":0.601,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_design","value":0.662,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":0.207892,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_design_output_tokens","value":46783,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_design__documents_docx","value":0.735,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_design__pdf","value":0.654,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"minimax/minimax-m3","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.638,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_long_agentic","value":0.11800000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":9.555722,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":508413,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.196,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.382,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_reasoning","value":0.8390000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.119001,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_reasoning_output_tokens","value":56566,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.808,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":0.93,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_reasoning__spatial","value":0.94,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.68,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_coding","value":0.6,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":0.982586,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_coding_output_tokens","value":45501,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_coding__llm_api_integration","value":0.683,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_coding__agent_loop","value":0.56,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_coding__billing_limits","value":0.458,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":0.472,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_coding__product_ux","value":0.556,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_coding__memory_tools","value":0.964,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_browser","value":0.08,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":0.450644,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_browser_output_tokens","value":6551,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.286,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_browser__sequential_planning","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_browser__structural_integrity","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_browser__constraint_adherence","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_data_analysis","value":0.765,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.133721,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":62776,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.805,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.491,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_research","value":0.281,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":2.327159,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_research_output_tokens","value":229696,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.335,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_research__legal","value":0.456,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_research__tax_finance","value":0.11,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_research__strategy","value":0.487,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_research__science_evidence","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_design","value":0.6559999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":0.388956,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_design_output_tokens","value":123574,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_design__documents_docx","value":0.811,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_design__pdf","value":0.521,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"mistralai/mistral-large-4-0","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.681,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_long_agentic","value":0.213,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":3.948783,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":122638,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0.042,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.042,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.679,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.367,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_reasoning","value":0.9,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.099368,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_reasoning_output_tokens","value":23381,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.808,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":0.952,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_reasoning__spatial","value":0.96,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.88,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_coding","value":0.782,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":1.465721,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_coding_output_tokens","value":35890,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_coding__llm_api_integration","value":0.625,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_coding__agent_loop","value":0.6,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_coding__billing_limits","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":0.917,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_coding__product_ux","value":0.778,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_coding__memory_tools","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_browser","value":0.36,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":2.494524,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_browser_output_tokens","value":36088,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.571,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_browser__sequential_planning","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":0.167,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_browser__structural_integrity","value":0.6,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_browser__constraint_adherence","value":0.333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_data_analysis","value":0.765,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.109447,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":25752,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.825,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.468,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_research","value":0.677,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":1.783182,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_research_output_tokens","value":28067,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.733,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_research__legal","value":0.966,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_research__tax_finance","value":0.501,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_research__strategy","value":0.554,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_research__science_evidence","value":0.575,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_design","value":0.6709999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":0.856232,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_design_output_tokens","value":44091,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_design__documents_docx","value":0.839,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_design__pdf","value":0.715,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.2","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.571,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_long_agentic","value":0.40399999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":8.83895,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":165448,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0.292,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0.069,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.699,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.615,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_reasoning","value":0.897,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.135723,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_reasoning_output_tokens","value":31620,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.846,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":0.98,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_reasoning__spatial","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.76,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_coding","value":0.902,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":1.371617,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_coding_output_tokens","value":34886,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_coding__llm_api_integration","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_coding__agent_loop","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_coding__billing_limits","value":0.958,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_coding__product_ux","value":0.722,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_coding__memory_tools","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_browser","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":1.689796,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_browser_output_tokens","value":21499,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.714,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_browser__sequential_planning","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_browser__structural_integrity","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_browser__constraint_adherence","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_data_analysis","value":0.7959999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.169429,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":38795,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.905,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.482,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_research","value":0.6859999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":2.694118,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_research_output_tokens","value":39607,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.879,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_research__legal","value":0.984,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_research__tax_finance","value":0.285,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_research__strategy","value":0.607,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_research__science_evidence","value":0.582,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_design","value":0.748,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":0.828624,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_design_output_tokens","value":48559,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_design__documents_docx","value":0.734,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_design__pdf","value":0.811,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-1.3","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.711,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_long_agentic","value":0.18899999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":4.833606,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":133814,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0.125,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.042,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.442,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.353,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_reasoning","value":0.737,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.042655,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_reasoning_output_tokens","value":9861,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.769,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":0.4,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_reasoning__spatial","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.78,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_coding","value":0.736,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":1.252538,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_coding_output_tokens","value":26529,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_coding__llm_api_integration","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_coding__agent_loop","value":0.78,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_coding__billing_limits","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":0.917,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_coding__product_ux","value":0.722,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_coding__memory_tools","value":0.902,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_browser","value":0.36,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":2.643368,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_browser_output_tokens","value":23505,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.571,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_browser__sequential_planning","value":0.25,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":0.167,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_browser__structural_integrity","value":0.2,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_browser__constraint_adherence","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_data_analysis","value":0.602,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.04491,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":9999,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.36,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.445,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_research","value":0.8029999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":0.732045,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_research_output_tokens","value":22757,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.767,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_research__legal","value":0.906,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_research__tax_finance","value":0.726,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_research__strategy","value":0.826,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_research__science_evidence","value":0.857,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_design","value":0.603,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":0.355892,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_design_output_tokens","value":32098,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_design__documents_docx","value":0.613,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_design__pdf","value":0.671,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"meta/muse-spark-open","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.553,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_long_agentic","value":0.158,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":2.047706,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":220348,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0.042,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.042,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.357,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.358,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_reasoning","value":0.7879999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.013351,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_reasoning_output_tokens","value":22764,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.769,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":0.802,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_reasoning__spatial","value":0.98,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.6,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_coding","value":0.655,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":0.330724,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_coding_output_tokens","value":46228,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_coding__llm_api_integration","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_coding__agent_loop","value":0.7,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_coding__billing_limits","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_coding__product_ux","value":0.333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_coding__memory_tools","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_browser","value":0.04,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":0.350916,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_browser_output_tokens","value":32614,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.143,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_browser__sequential_planning","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_browser__structural_integrity","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_browser__constraint_adherence","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_data_analysis","value":0.6459999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.019417,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":31654,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.496,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.443,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_research","value":0.7090000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":0.166773,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_research_output_tokens","value":44246,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.644,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_research__legal","value":0.775,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_research__tax_finance","value":0.695,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_research__strategy","value":0.656,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_research__science_evidence","value":0.849,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_design","value":0.607,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":0.055756,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_design_output_tokens","value":32708,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_design__documents_docx","value":0.752,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_design__pdf","value":0.578,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.567,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_long_agentic","value":0.27899999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":7.184067,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":366727,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0.083,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.25,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.673,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.416,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_reasoning","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.074916,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_reasoning_output_tokens","value":24786,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.596,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":0.965,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_reasoning__spatial","value":0.96,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.68,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_coding","value":0.868,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":0.69,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_coding_output_tokens","value":43464,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_coding__llm_api_integration","value":0.875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_coding__agent_loop","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_coding__billing_limits","value":0.792,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":0.861,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_coding__product_ux","value":0.722,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_coding__memory_tools","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_browser","value":0.32,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":1.290276,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_browser_output_tokens","value":49468,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.571,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_browser__sequential_planning","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_browser__structural_integrity","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_browser__constraint_adherence","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_data_analysis","value":0.7659999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.089032,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":29045,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.849,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.488,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":0.961,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_research","value":0.594,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":1.127464,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_research_output_tokens","value":84200,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.635,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_research__legal","value":0.765,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_research__tax_finance","value":0.379,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_research__strategy","value":0.594,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_research__science_evidence","value":0.628,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_design","value":0.759,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":0.383612,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_design_output_tokens","value":63352,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_design__documents_docx","value":0.799,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_design__pdf","value":0.823,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-27b","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.699,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_long_agentic","value":0.371,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":1.872044,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":459461,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0.125,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.458,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0.181,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.653,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.462,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_reasoning","value":0.8740000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.021988,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_reasoning_output_tokens","value":46396,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.808,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":0.988,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_reasoning__spatial","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.7,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_coding","value":0.8740000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":0.106138,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_coding_output_tokens","value":35754,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_coding__llm_api_integration","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_coding__agent_loop","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_coding__billing_limits","value":0.958,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":0.917,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_coding__product_ux","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_coding__memory_tools","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_browser","value":0.48,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":0.224024,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_browser_output_tokens","value":35680,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.429,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_browser__sequential_planning","value":0.25,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_browser__structural_integrity","value":0.6,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_browser__constraint_adherence","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_data_analysis","value":0.742,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.043452,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":90692,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.756,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.51,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":0.961,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_research","value":0.746,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":0.316805,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_research_output_tokens","value":115708,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.682,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_research__legal","value":0.926,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_research__tax_finance","value":0.719,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_research__strategy","value":0.545,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_research__science_evidence","value":0.903,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_design","value":0.728,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":0.128072,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_design_output_tokens","value":84253,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_design__documents_docx","value":0.816,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_design__pdf","value":0.708,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-flash","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.706,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_long_agentic","value":0.423,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":14.93005,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":386822,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0.291,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.229,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0.125,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.814,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.678,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_reasoning","value":0.882,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.131491,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_reasoning_output_tokens","value":21515,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.788,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_reasoning__spatial","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.74,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_coding","value":0.603,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":1.986917,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_coding_output_tokens","value":167999,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_coding__llm_api_integration","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_coding__agent_loop","value":0.6,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_coding__billing_limits","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":0.333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_coding__product_ux","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_coding__memory_tools","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_browser","value":0.32,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":1.542556,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_browser_output_tokens","value":45240,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.429,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_browser__sequential_planning","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_browser__structural_integrity","value":0.2,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_browser__constraint_adherence","value":0.333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_data_analysis","value":0.784,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.218946,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":34658,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.871,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.501,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":0.98,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_research","value":0.6990000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":1.954673,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_research_output_tokens","value":105534,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.73,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_research__legal","value":0.901,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_research__tax_finance","value":0.578,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_research__strategy","value":0.71,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_research__science_evidence","value":0.55,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_design","value":0.7859999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":0.59624,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_design_output_tokens","value":45551,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_design__documents_docx","value":0.787,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_design__pdf","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"qwen/qwen3.8-max-0902","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.775,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_long_agentic","value":0.275,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_long_agentic_cost_per_task_usd","value":10.375628,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_long_agentic_output_tokens","value":493230,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_long_agentic__finance_compliance_apps","value":0.042,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_long_agentic__operations_commerce_apps","value":0.167,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_long_agentic__long_run_operations","value":0.056,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_long_agentic__systems_engineering","value":0.752,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_long_agentic__performance_optimisation","value":0.425,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_reasoning","value":0.838,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_reasoning_cost_per_task_usd","value":0.048211,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_reasoning_output_tokens","value":17443,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_reasoning__theory_of_mind","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_reasoning__zebra_puzzles","value":0.9,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_reasoning__spatial","value":0.98,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_reasoning__logic_with_navigation","value":0.72,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_coding","value":0.856,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_coding_cost_per_task_usd","value":1.095317,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_coding_output_tokens","value":43804,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_coding__llm_api_integration","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_coding__agent_loop","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_coding__billing_limits","value":0.708,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_coding__cloud_infrastructure","value":0.778,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_coding__product_ux","value":0.722,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_coding__memory_tools","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_browser","value":0.24,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_browser_cost_per_task_usd","value":2.791736,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_browser_output_tokens","value":107108,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_browser__data_aggregation","value":0.286,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_browser__sequential_planning","value":0.25,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_browser__analysis_driven_action","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_browser__structural_integrity","value":0.4,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_browser__constraint_adherence","value":0.333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_data_analysis","value":0.635,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_data_analysis_cost_per_task_usd","value":0.063898,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_data_analysis_output_tokens","value":22293,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_data_analysis__consecutive_events","value":0.424,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_data_analysis__table_join","value":0.501,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_data_analysis__table_reformat","value":0.98,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_research","value":0.728,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_research_cost_per_task_usd","value":1.228914,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_research_output_tokens","value":72511,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_research__regulatory_compliance","value":0.673,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_research__legal","value":0.696,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_research__tax_finance","value":0.712,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_research__strategy","value":0.814,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_research__science_evidence","value":0.843,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_design","value":0.769,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/table.csv"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_design_cost_per_task_usd","value":0.745688,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_design_output_tokens","value":71830,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/cost.csv"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_design__documents_docx","value":0.827,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_design__pdf","value":0.729,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"stepfun/step-5-preview","source":"livebench","metric":"livebench_design__presentations_ppt","value":0.771,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://livebench.ai/data/20261014/breakdown.json"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.9238,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":20.59,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"anthropic/claude-opus-5","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.9159,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"anthropic/claude-opus-5","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":9.6,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"anthropic/claude-fable-5","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.915,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"anthropic/claude-fable-5","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":25,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.9098999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":23.91,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"google/gemini-3.8-flash","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.9022,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"google/gemini-3.8-flash","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":7.82,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"google/gemini-3.7-flash","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.9012,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"google/gemini-3.7-flash","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":4.16,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8987,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":188,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8957999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":23.44,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"google/gemini-3.5-flash","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8952,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"google/gemini-3.5-flash","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":26.26,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"x-ai/grok-4.6","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.894,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"x-ai/grok-4.6","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":54.98,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"qwen/qwen3.7-max","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8931,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"qwen/qwen3.7-max","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":29.15,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"google/gemini-3.6-flash","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8928,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"google/gemini-3.6-flash","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":7.3,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"x-ai/grok-4.5","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8922,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"x-ai/grok-4.5","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":358,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"anthropic/claude-opus-4.6","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8911,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"anthropic/claude-opus-4.6","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":49.45,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-5.6-sol","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8909999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-5.6-sol","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":15.65,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"meta/muse-spark-1.1","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8873000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"meta/muse-spark-1.1","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":21.03,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8859999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":63.58,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"google/gemini-3-flash-preview","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8859,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"google/gemini-3-flash-preview","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":36.25,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"meta/muse-spark-1.2","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8828,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"meta/muse-spark-1.2","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":44.23,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-5.5","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8814,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-5.5","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":42.11,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"moonshotai/kimi-k3","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8797,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"moonshotai/kimi-k3","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":38.72,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"anthropic/claude-opus-4.1","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8792,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"anthropic/claude-opus-4.1","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":27.67,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"qwen/qwen3.6-plus","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8767,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"qwen/qwen3.6-plus","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":46.18,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8756999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":156,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8755,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":25.19,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-5.4","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8748,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-5.4","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":28.88,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8736,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":38.2,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8734000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":55.41,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8726,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":38.92,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8725,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":578,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8718,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":76.68,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"minimax/minimax-m2.1","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8704999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"minimax/minimax-m2.1","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":40.96,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8697,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":59.62,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"z-ai/glm-5.1","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8690000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"z-ai/glm-5.1","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":69.32,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"z-ai/glm-5.3","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8676999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"z-ai/glm-5.3","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":61.78,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"z-ai/glm-5.2","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8671,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"z-ai/glm-5.2","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":51.64,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-5.6-terra","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8665999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-5.6-terra","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":8.17,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-5","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8654000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-5","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":37.24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-5.1","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8637999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-5.1","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":23.06,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"thinkingmachines/inkling","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.863,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"thinkingmachines/inkling","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":73.26,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"x-ai/grok-4.20","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8625,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"x-ai/grok-4.20","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":11.65,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8623999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":14.51,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-5.2","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8623000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-5.2","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":35.41,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8621,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":17.19,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8606,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":44.76,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-5.6-luna","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8604,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-5.6-luna","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":16.95,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"z-ai/glm-5","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8603000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"z-ai/glm-5","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":86.89,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8591,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":39.2,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"x-ai/grok-4.3","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8584,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"x-ai/grok-4.3","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":637,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8584,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":4.82,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8576,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":32.92,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/o3","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8559,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/o3","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":16.73,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"thinkingmachines/inkling-small","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8556999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"thinkingmachines/inkling-small","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":71.69,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"deepseek/deepseek-v3.2","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8492000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"deepseek/deepseek-v3.2","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":90.15,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8459,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":67.76,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-5.4-mini","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8454999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-5.4-mini","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":20,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"qwen/qwen3.8-27b","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8434,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"qwen/qwen3.8-27b","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":69.85,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"minimax/minimax-m3","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8422,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"minimax/minimax-m3","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":41.39,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8406,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":33.3,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/o1","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8349,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/o1","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":26.87,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8293,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":30.25,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"z-ai/glm-4.7","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8273999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"z-ai/glm-4.7","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":104.45,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-5-mini","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8223,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-5-mini","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":22.2,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"z-ai/glm-4.6","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8220000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"z-ai/glm-4.6","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":47,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8201,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":20.07,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"z-ai/glm-4.5","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8122,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"z-ai/glm-4.5","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":137,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"moonshotai/kimi-k2-thinking","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8107,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"moonshotai/kimi-k2-thinking","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":94.77,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/o4-mini","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8056,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/o4-mini","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":10.44,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-4.1","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.805,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-4.1","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":8.18,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"minimax/minimax-m2.7","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8043,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"minimax/minimax-m2.7","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":50.01,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"minimax/minimax-m2.5","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.8009000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"minimax/minimax-m2.5","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":48.27,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"mistralai/mistral-large-2512","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.7981999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"mistralai/mistral-large-2512","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":13.55,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.7947,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":25.05,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"meta-llama/llama-4-maverick","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.7942,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"meta-llama/llama-4-maverick","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":6.8,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"moonshotai/kimi-k2","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.7939,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"moonshotai/kimi-k2","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":20.34,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-oss-120b","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.7917000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-oss-120b","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":35.41,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"google/gemini-2.5-flash-lite","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.7912,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"google/gemini-2.5-flash-lite","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":9.62,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.7872,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":25.78,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/o3-mini","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.7868999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/o3-mini","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":22.38,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-4.1-mini","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.7722,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-4.1-mini","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":3.83,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-5.4-nano","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.7717,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-5.4-nano","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":8.21,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-5-nano","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.7606999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-5-nano","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":26.11,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.7533,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":66.38,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"mistralai/mistral-medium-3.1","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.7529,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"mistralai/mistral-medium-3.1","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":8.83,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-4o-2024-08-06","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.7413,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-4o-2024-08-06","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":9,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-4o-2024-11-20","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.7256,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-4o-2024-11-20","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":9.14,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-oss-20b","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.7164,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-oss-20b","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":30.21,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"mistralai/mistral-large","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.6970999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"mistralai/mistral-large","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":7.19,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"meta-llama/llama-4-scout","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.6962999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"meta-llama/llama-4-scout","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":5.34,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"cohere/command-a","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.6917,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"cohere/command-a","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":9.85,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-4.1-nano","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.6347999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-4.1-nano","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":2.4,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-4o-mini","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy","value":0.6273,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"openai/gpt-4o-mini","source":"vals-mmlu-pro","metric":"mmlu_pro_accuracy_latency_seconds","value":5.09,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro"},{"modelId":"anthropic/claude-sonnet-5.5","source":"valsai","metric":"valsai_index","value":0.7084999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"anthropic/claude-sonnet-5.5","source":"valsai","metric":"valsai_index_cost_per_test_usd","value":18.7,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"anthropic/claude-sonnet-5.5","source":"valsai","metric":"valsai_index_duration_seconds","value":5160,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"anthropic/claude-opus-5.5","source":"valsai","metric":"valsai_index","value":0.7018000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"anthropic/claude-opus-5.5","source":"valsai","metric":"valsai_index_cost_per_test_usd","value":28.12,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"anthropic/claude-opus-5.5","source":"valsai","metric":"valsai_index_duration_seconds","value":5100,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"google/gemini-4-argon","source":"valsai","metric":"valsai_index","value":0.6923999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"google/gemini-4-argon","source":"valsai","metric":"valsai_index_cost_per_test_usd","value":13.37,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"google/gemini-4-argon","source":"valsai","metric":"valsai_index_duration_seconds","value":2698,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"openai/gpt-6-astra","source":"valsai","metric":"valsai_index","value":0.6502,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"openai/gpt-6-astra","source":"valsai","metric":"valsai_index_cost_per_test_usd","value":21.28,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"openai/gpt-6-astra","source":"valsai","metric":"valsai_index_duration_seconds","value":2019,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"meta/muse-wonder","source":"valsai","metric":"valsai_index","value":0.6487999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"meta/muse-wonder","source":"valsai","metric":"valsai_index_cost_per_test_usd","value":10.65,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"meta/muse-wonder","source":"valsai","metric":"valsai_index_duration_seconds","value":2124,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"openai/gpt-6.1-sol","source":"valsai","metric":"valsai_index","value":0.6394,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"openai/gpt-6.1-sol","source":"valsai","metric":"valsai_index_cost_per_test_usd","value":3.61,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"openai/gpt-6.1-sol","source":"valsai","metric":"valsai_index_duration_seconds","value":2664,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"valsai","metric":"valsai_index","value":0.6126,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"valsai","metric":"valsai_index_cost_per_test_usd","value":0.66,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"valsai","metric":"valsai_index_duration_seconds","value":2395,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"z-ai/glm-5.3","source":"valsai","metric":"valsai_index","value":0.5972999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"z-ai/glm-5.3","source":"valsai","metric":"valsai_index_cost_per_test_usd","value":8.52,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"z-ai/glm-5.3","source":"valsai","metric":"valsai_index_duration_seconds","value":3840,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"anthropic/claude-haiku-5.5","source":"valsai","metric":"valsai_index","value":0.5871,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"anthropic/claude-haiku-5.5","source":"valsai","metric":"valsai_index_cost_per_test_usd","value":3.17,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"anthropic/claude-haiku-5.5","source":"valsai","metric":"valsai_index_duration_seconds","value":2988,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"x-ai/grok-4.7","source":"valsai","metric":"valsai_index","value":0.5856,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"x-ai/grok-4.7","source":"valsai","metric":"valsai_index_cost_per_test_usd","value":11.63,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"x-ai/grok-4.7","source":"valsai","metric":"valsai_index_duration_seconds","value":2014,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"valsai","metric":"valsai_index","value":0.5781000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"valsai","metric":"valsai_index_cost_per_test_usd","value":0.43,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"valsai","metric":"valsai_index_duration_seconds","value":4380,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"google/gemini-3.8-flash","source":"valsai","metric":"valsai_index","value":0.5595,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"google/gemini-3.8-flash","source":"valsai","metric":"valsai_index_cost_per_test_usd","value":6.06,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"google/gemini-3.8-flash","source":"valsai","metric":"valsai_index_duration_seconds","value":2158,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"valsai","metric":"valsai_index","value":0.5483,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"valsai","metric":"valsai_index_cost_per_test_usd","value":0.22,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"valsai","metric":"valsai_index_duration_seconds","value":4020,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"tencent/hy4-preview","source":"valsai","metric":"valsai_index","value":0.5321,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"tencent/hy4-preview","source":"valsai","metric":"valsai_index_cost_per_test_usd","value":1.45,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"tencent/hy4-preview","source":"valsai","metric":"valsai_index_duration_seconds","value":3563,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"valsai","metric":"valsai_index","value":0.5297,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"valsai","metric":"valsai_index_cost_per_test_usd","value":2.5,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"valsai","metric":"valsai_index_duration_seconds","value":3483,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"moonshotai/kimi-k3","source":"valsai","metric":"valsai_index","value":0.5295000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"moonshotai/kimi-k3","source":"valsai","metric":"valsai_index_cost_per_test_usd","value":7.17,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"moonshotai/kimi-k3","source":"valsai","metric":"valsai_index_duration_seconds","value":4500,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"openai/gpt-6-luna","source":"valsai","metric":"valsai_index","value":0.5232,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"openai/gpt-6-luna","source":"valsai","metric":"valsai_index_cost_per_test_usd","value":0.45,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"openai/gpt-6-luna","source":"valsai","metric":"valsai_index_duration_seconds","value":1943,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"z-ai/glm-5.3-flash","source":"valsai","metric":"valsai_index","value":0.5085999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"z-ai/glm-5.3-flash","source":"valsai","metric":"valsai_index_cost_per_test_usd","value":1.13,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"z-ai/glm-5.3-flash","source":"valsai","metric":"valsai_index_duration_seconds","value":3840,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"thinkingmachines/inkling","source":"valsai","metric":"valsai_index","value":0.2896,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"thinkingmachines/inkling","source":"valsai","metric":"valsai_index_cost_per_test_usd","value":1.85,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"thinkingmachines/inkling","source":"valsai","metric":"valsai_index_duration_seconds","value":1033,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"thinkingmachines/inkling-small","source":"valsai","metric":"valsai_index","value":0.2759,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"thinkingmachines/inkling-small","source":"valsai","metric":"valsai_index_cost_per_test_usd","value":0.4,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"thinkingmachines/inkling-small","source":"valsai","metric":"valsai_index_duration_seconds","value":986,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_index"},{"modelId":"anthropic/claude-opus-5.5","source":"aa-api","metric":"aa_hle","value":0.614,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-5.5","source":"aa-api","metric":"aa_scicode","value":0.669,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-5.5","source":"aa-api","metric":"aa_long_context_reasoning","value":0.846666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-sonnet-5.5","source":"aa-api","metric":"aa_hle","value":0.55,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-sonnet-5.5","source":"aa-api","metric":"aa_scicode","value":0.61,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-sonnet-5.5","source":"aa-api","metric":"aa_long_context_reasoning","value":0.826666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-fable-5.1","source":"aa-api","metric":"aa_gpqa","value":0.937,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-fable-5.1","source":"aa-api","metric":"aa_hle","value":0.591,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-fable-5.1","source":"aa-api","metric":"aa_scicode","value":0.631,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-fable-5.1","source":"aa-api","metric":"aa_long_context_reasoning","value":0.853333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-6-astra","source":"aa-api","metric":"aa_gpqa","value":0.963,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-6-astra","source":"aa-api","metric":"aa_hle","value":0.547,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-6-astra","source":"aa-api","metric":"aa_scicode","value":0.565,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-6-astra","source":"aa-api","metric":"aa_long_context_reasoning","value":0.806666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-4-argon","source":"aa-api","metric":"aa_hle","value":0.571,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-4-argon","source":"aa-api","metric":"aa_scicode","value":0.618,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-4-argon","source":"aa-api","metric":"aa_long_context_reasoning","value":0.796666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta/muse-wonder","source":"aa-api","metric":"aa_hle","value":0.501,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta/muse-wonder","source":"aa-api","metric":"aa_scicode","value":0.603,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta/muse-wonder","source":"aa-api","metric":"aa_long_context_reasoning","value":0.806666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-6.1-sol","source":"aa-api","metric":"aa_hle","value":0.529,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-6.1-sol","source":"aa-api","metric":"aa_scicode","value":0.558,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-6.1-sol","source":"aa-api","metric":"aa_long_context_reasoning","value":0.84,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-5","source":"aa-api","metric":"aa_gpqa","value":0.937,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-5","source":"aa-api","metric":"aa_hle","value":0.549,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-5","source":"aa-api","metric":"aa_scicode","value":0.564,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-5","source":"aa-api","metric":"aa_long_context_reasoning","value":0.82,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-fable-5","source":"aa-api","metric":"aa_gpqa","value":0.926,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-fable-5","source":"aa-api","metric":"aa_hle","value":0.555,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-fable-5","source":"aa-api","metric":"aa_scicode","value":0.61,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-fable-5","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.628787878787879,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-fable-5","source":"aa-api","metric":"aa_ifbench","value":0.63469387755102,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-fable-5","source":"aa-api","metric":"aa_long_context_reasoning","value":0.823333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-fable-5","source":"aa-api","metric":"aa_tau2","value":0.985380116959064,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta/muse-spark-1.3","source":"aa-api","metric":"aa_gpqa","value":0.941,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta/muse-spark-1.3","source":"aa-api","metric":"aa_hle","value":0.487,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta/muse-spark-1.3","source":"aa-api","metric":"aa_scicode","value":0.597,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta/muse-spark-1.3","source":"aa-api","metric":"aa_long_context_reasoning","value":0.83,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-6-sol","source":"aa-api","metric":"aa_hle","value":0.479,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-6-sol","source":"aa-api","metric":"aa_scicode","value":0.576,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-6-sol","source":"aa-api","metric":"aa_long_context_reasoning","value":0.836666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.6-sol","source":"aa-api","metric":"aa_gpqa","value":0.941,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.6-sol","source":"aa-api","metric":"aa_hle","value":0.495,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.6-sol","source":"aa-api","metric":"aa_scicode","value":0.578,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.6-sol","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.659090909090909,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.6-sol","source":"aa-api","metric":"aa_ifbench","value":0.726530612244898,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.6-sol","source":"aa-api","metric":"aa_long_context_reasoning","value":0.84,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.6-sol","source":"aa-api","metric":"aa_tau2","value":0.850877192982456,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"x-ai/grok-4.7","source":"aa-api","metric":"aa_hle","value":0.431,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"x-ai/grok-4.7","source":"aa-api","metric":"aa_scicode","value":0.578,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"x-ai/grok-4.7","source":"aa-api","metric":"aa_long_context_reasoning","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"aa-api","metric":"aa_hle","value":0.494,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"aa-api","metric":"aa_scicode","value":0.609,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"aa-api","metric":"aa_long_context_reasoning","value":0.863333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.8-max-0902","source":"aa-api","metric":"aa_gpqa","value":0.928,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.8-max-0902","source":"aa-api","metric":"aa_hle","value":0.431,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.8-max-0902","source":"aa-api","metric":"aa_scicode","value":0.532,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.8-max-0902","source":"aa-api","metric":"aa_long_context_reasoning","value":0.803333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"aa-api","metric":"aa_hle","value":0.433,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"aa-api","metric":"aa_scicode","value":0.559,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"aa-api","metric":"aa_long_context_reasoning","value":0.826666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5.3","source":"aa-api","metric":"aa_gpqa","value":0.917,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5.3","source":"aa-api","metric":"aa_hle","value":0.423,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5.3","source":"aa-api","metric":"aa_scicode","value":0.59,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5.3","source":"aa-api","metric":"aa_long_context_reasoning","value":0.796666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"x-ai/grok-4.6","source":"aa-api","metric":"aa_gpqa","value":0.949,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"x-ai/grok-4.6","source":"aa-api","metric":"aa_hle","value":0.441,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"x-ai/grok-4.6","source":"aa-api","metric":"aa_scicode","value":0.565,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"x-ai/grok-4.6","source":"aa-api","metric":"aa_long_context_reasoning","value":0.81,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"stepfun/step-5-preview","source":"aa-api","metric":"aa_hle","value":0.465,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"stepfun/step-5-preview","source":"aa-api","metric":"aa_scicode","value":0.589,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"stepfun/step-5-preview","source":"aa-api","metric":"aa_long_context_reasoning","value":0.883333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k3","source":"aa-api","metric":"aa_gpqa","value":0.935,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k3","source":"aa-api","metric":"aa_hle","value":0.469,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k3","source":"aa-api","metric":"aa_scicode","value":0.595,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k3","source":"aa-api","metric":"aa_long_context_reasoning","value":0.886666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-haiku-5.5","source":"aa-api","metric":"aa_hle","value":0.444,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-haiku-5.5","source":"aa-api","metric":"aa_scicode","value":0.55,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-haiku-5.5","source":"aa-api","metric":"aa_long_context_reasoning","value":0.826666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.6-terra","source":"aa-api","metric":"aa_gpqa","value":0.925,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.6-terra","source":"aa-api","metric":"aa_hle","value":0.429,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.6-terra","source":"aa-api","metric":"aa_scicode","value":0.55,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.6-terra","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.628787878787879,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.6-terra","source":"aa-api","metric":"aa_ifbench","value":0.712244897959184,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.6-terra","source":"aa-api","metric":"aa_long_context_reasoning","value":0.83,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.6-terra","source":"aa-api","metric":"aa_tau2","value":0.862573099415205,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5.3-flash","source":"aa-api","metric":"aa_gpqa","value":0.912,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5.3-flash","source":"aa-api","metric":"aa_hle","value":0.399,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5.3-flash","source":"aa-api","metric":"aa_scicode","value":0.516,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5.3-flash","source":"aa-api","metric":"aa_long_context_reasoning","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-4.8","source":"aa-api","metric":"aa_gpqa","value":0.92,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-4.8","source":"aa-api","metric":"aa_hle","value":0.487,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-4.8","source":"aa-api","metric":"aa_scicode","value":0.544,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-4.8","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.583333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-4.8","source":"aa-api","metric":"aa_ifbench","value":0.622448979591837,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-4.8","source":"aa-api","metric":"aa_long_context_reasoning","value":0.776666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-4.8","source":"aa-api","metric":"aa_tau2","value":0.944444444444445,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"inclusionai/ling-3.1-flash","source":"aa-api","metric":"aa_hle","value":0.394,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"inclusionai/ling-3.1-flash","source":"aa-api","metric":"aa_scicode","value":0.541,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"inclusionai/ling-3.1-flash","source":"aa-api","metric":"aa_long_context_reasoning","value":0.83,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.8-flash","source":"aa-api","metric":"aa_gpqa","value":0.953,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.8-flash","source":"aa-api","metric":"aa_hle","value":0.478,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.8-flash","source":"aa-api","metric":"aa_scicode","value":0.566,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.8-flash","source":"aa-api","metric":"aa_long_context_reasoning","value":0.84,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-4.7","source":"aa-api","metric":"aa_gpqa","value":0.914,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-4.7","source":"aa-api","metric":"aa_hle","value":0.423,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-4.7","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.545454545454545,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-4.7","source":"aa-api","metric":"aa_ifbench","value":0.586394557823129,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-4.7","source":"aa-api","metric":"aa_long_context_reasoning","value":0.786666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-4.7","source":"aa-api","metric":"aa_tau2","value":0.885964912280702,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.8-2.4t-a95b","source":"aa-api","metric":"aa_gpqa","value":0.935,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.8-2.4t-a95b","source":"aa-api","metric":"aa_hle","value":0.424,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.8-2.4t-a95b","source":"aa-api","metric":"aa_scicode","value":0.541,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.8-2.4t-a95b","source":"aa-api","metric":"aa_long_context_reasoning","value":0.803333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.7-flash","source":"aa-api","metric":"aa_gpqa","value":0.945,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.7-flash","source":"aa-api","metric":"aa_hle","value":0.479,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.7-flash","source":"aa-api","metric":"aa_scicode","value":0.598,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.7-flash","source":"aa-api","metric":"aa_long_context_reasoning","value":0.83,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta/muse-spark-1.2","source":"aa-api","metric":"aa_gpqa","value":0.904,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta/muse-spark-1.2","source":"aa-api","metric":"aa_hle","value":0.455,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta/muse-spark-1.2","source":"aa-api","metric":"aa_scicode","value":0.574,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta/muse-spark-1.2","source":"aa-api","metric":"aa_long_context_reasoning","value":0.79,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"aa-api","metric":"aa_hle","value":0.392,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"aa-api","metric":"aa_scicode","value":0.519,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"aa-api","metric":"aa_long_context_reasoning","value":0.84,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.4","source":"aa-api","metric":"aa_gpqa","value":0.92,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.4","source":"aa-api","metric":"aa_hle","value":0.437,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.4","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.575757575757576,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.4","source":"aa-api","metric":"aa_ifbench","value":0.739455782312925,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.4","source":"aa-api","metric":"aa_long_context_reasoning","value":0.82,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.4","source":"aa-api","metric":"aa_tau2","value":0.871345029239766,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta/muse-spark-open","source":"aa-api","metric":"aa_gpqa","value":0.89,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta/muse-spark-open","source":"aa-api","metric":"aa_hle","value":0.439,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta/muse-spark-open","source":"aa-api","metric":"aa_scicode","value":0.584,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta/muse-spark-open","source":"aa-api","metric":"aa_long_context_reasoning","value":0.783333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"x-ai/grok-4.5","source":"aa-api","metric":"aa_gpqa","value":0.931,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"x-ai/grok-4.5","source":"aa-api","metric":"aa_hle","value":0.427,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"x-ai/grok-4.5","source":"aa-api","metric":"aa_scicode","value":0.55,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"x-ai/grok-4.5","source":"aa-api","metric":"aa_long_context_reasoning","value":0.793333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-large-4-0","source":"aa-api","metric":"aa_hle","value":0.35,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-large-4-0","source":"aa-api","metric":"aa_scicode","value":0.542,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-large-4-0","source":"aa-api","metric":"aa_long_context_reasoning","value":0.813333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.5","source":"aa-api","metric":"aa_gpqa","value":0.935,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.5","source":"aa-api","metric":"aa_hle","value":0.458,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.5","source":"aa-api","metric":"aa_scicode","value":0.561,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.5","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.606060606060606,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.5","source":"aa-api","metric":"aa_ifbench","value":0.758503401360544,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.5","source":"aa-api","metric":"aa_long_context_reasoning","value":0.843333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.5","source":"aa-api","metric":"aa_tau2","value":0.93859649122807,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-sonnet-5","source":"aa-api","metric":"aa_gpqa","value":0.911,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-sonnet-5","source":"aa-api","metric":"aa_hle","value":0.413,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-sonnet-5","source":"aa-api","metric":"aa_scicode","value":0.543,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-sonnet-5","source":"aa-api","metric":"aa_long_context_reasoning","value":0.82,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-6-luna","source":"aa-api","metric":"aa_hle","value":0.385,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-6-luna","source":"aa-api","metric":"aa_scicode","value":0.546,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-6-luna","source":"aa-api","metric":"aa_long_context_reasoning","value":0.833333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"aa-api","metric":"aa_hle","value":0.351,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"aa-api","metric":"aa_scicode","value":0.513,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"aa-api","metric":"aa_long_context_reasoning","value":0.743333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.6-luna","source":"aa-api","metric":"aa_gpqa","value":0.911,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.6-luna","source":"aa-api","metric":"aa_hle","value":0.395,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.6-luna","source":"aa-api","metric":"aa_scicode","value":0.536,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.6-luna","source":"aa-api","metric":"aa_long_context_reasoning","value":0.836666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"aa-api","metric":"aa_gpqa","value":0.928,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"aa-api","metric":"aa_hle","value":0.41,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"aa-api","metric":"aa_scicode","value":0.51,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"aa-api","metric":"aa_long_context_reasoning","value":0.803333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"aa-api","metric":"aa_gpqa","value":0.913,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"aa-api","metric":"aa_hle","value":0.345,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"aa-api","metric":"aa_scicode","value":0.497,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"aa-api","metric":"aa_long_context_reasoning","value":0.813333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"aa-api","metric":"aa_gpqa","value":0.908,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"aa-api","metric":"aa_hle","value":0.386,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"aa-api","metric":"aa_scicode","value":0.503,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"aa-api","metric":"aa_long_context_reasoning","value":0.796666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.6-flash","source":"aa-api","metric":"aa_gpqa","value":0.928,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.6-flash","source":"aa-api","metric":"aa_hle","value":0.408,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.6-flash","source":"aa-api","metric":"aa_scicode","value":0.534,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.6-flash","source":"aa-api","metric":"aa_long_context_reasoning","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta/muse-spark-1.1","source":"aa-api","metric":"aa_gpqa","value":0.898,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta/muse-spark-1.1","source":"aa-api","metric":"aa_hle","value":0.462,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta/muse-spark-1.1","source":"aa-api","metric":"aa_scicode","value":0.588,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta/muse-spark-1.1","source":"aa-api","metric":"aa_long_context_reasoning","value":0.776666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5.2","source":"aa-api","metric":"aa_gpqa","value":0.895,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5.2","source":"aa-api","metric":"aa_hle","value":0.411,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5.2","source":"aa-api","metric":"aa_scicode","value":0.512,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5.2","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.507575757575758,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5.2","source":"aa-api","metric":"aa_ifbench","value":0.733333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5.2","source":"aa-api","metric":"aa_long_context_reasoning","value":0.783333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5.2","source":"aa-api","metric":"aa_tau2","value":0.991228070175439,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.8-27b","source":"aa-api","metric":"aa_gpqa","value":0.905,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.8-27b","source":"aa-api","metric":"aa_hle","value":0.339,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.8-27b","source":"aa-api","metric":"aa_scicode","value":0.466,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.8-27b","source":"aa-api","metric":"aa_long_context_reasoning","value":0.82,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.5-flash","source":"aa-api","metric":"aa_gpqa","value":0.922,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.5-flash","source":"aa-api","metric":"aa_hle","value":0.427,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.5-flash","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.462121212121212,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.5-flash","source":"aa-api","metric":"aa_ifbench","value":0.763265306122449,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.5-flash","source":"aa-api","metric":"aa_long_context_reasoning","value":0.743333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.5-flash","source":"aa-api","metric":"aa_tau2","value":0.956140350877193,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.5-flash","source":"aa-api","metric":"aa_scicode","value":0.539,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.3-codex","source":"aa-api","metric":"aa_gpqa","value":0.915,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.3-codex","source":"aa-api","metric":"aa_hle","value":0.425,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.3-codex","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.53030303030303,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.3-codex","source":"aa-api","metric":"aa_ifbench","value":0.753741496598639,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.3-codex","source":"aa-api","metric":"aa_long_context_reasoning","value":0.833333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.3-codex","source":"aa-api","metric":"aa_tau2","value":0.859649122807018,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-4.6","source":"aa-api","metric":"aa_gpqa","value":0.896,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-4.6","source":"aa-api","metric":"aa_hle","value":0.399,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-4.6","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.484848484848485,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-4.6","source":"aa-api","metric":"aa_ifbench","value":0.531292517006803,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-4.6","source":"aa-api","metric":"aa_long_context_reasoning","value":0.78,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-4.6","source":"aa-api","metric":"aa_tau2","value":0.921052631578947,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.2","source":"aa-api","metric":"aa_math_index","value":99,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.2","source":"aa-api","metric":"aa_gpqa","value":0.903,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.2","source":"aa-api","metric":"aa_hle","value":0.377,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.2","source":"aa-api","metric":"aa_mmlu_pro","value":0.874,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.2","source":"aa-api","metric":"aa_livecodebench","value":0.894,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.2","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.46969696969697,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.2","source":"aa-api","metric":"aa_ifbench","value":0.754421768707483,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.2","source":"aa-api","metric":"aa_long_context_reasoning","value":0.826666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.2","source":"aa-api","metric":"aa_tau2","value":0.847953216374269,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.2","source":"aa-api","metric":"aa_aime_2025","value":0.99,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-sonnet-4.6","source":"aa-api","metric":"aa_gpqa","value":0.875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-sonnet-4.6","source":"aa-api","metric":"aa_hle","value":0.336,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-sonnet-4.6","source":"aa-api","metric":"aa_scicode","value":0.501,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-sonnet-4.6","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.53030303030303,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-sonnet-4.6","source":"aa-api","metric":"aa_ifbench","value":0.565986394557823,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-sonnet-4.6","source":"aa-api","metric":"aa_long_context_reasoning","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-sonnet-4.6","source":"aa-api","metric":"aa_tau2","value":0.795321637426901,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.1-pro-preview","source":"aa-api","metric":"aa_gpqa","value":0.941,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.1-pro-preview","source":"aa-api","metric":"aa_hle","value":0.47,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.1-pro-preview","source":"aa-api","metric":"aa_scicode","value":0.587,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.1-pro-preview","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.537878787878788,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.1-pro-preview","source":"aa-api","metric":"aa_ifbench","value":0.771428571428571,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.1-pro-preview","source":"aa-api","metric":"aa_long_context_reasoning","value":0.82,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.1-pro-preview","source":"aa-api","metric":"aa_tau2","value":0.956140350877193,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.7-max","source":"aa-api","metric":"aa_gpqa","value":0.923,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.7-max","source":"aa-api","metric":"aa_hle","value":0.405,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.7-max","source":"aa-api","metric":"aa_scicode","value":0.495,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.7-max","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.507575757575758,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.7-max","source":"aa-api","metric":"aa_ifbench","value":0.805442176870748,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.7-max","source":"aa-api","metric":"aa_long_context_reasoning","value":0.79,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.7-max","source":"aa-api","metric":"aa_tau2","value":0.947368421052632,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m3","source":"aa-api","metric":"aa_gpqa","value":0.929,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m3","source":"aa-api","metric":"aa_hle","value":0.39,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m3","source":"aa-api","metric":"aa_scicode","value":0.471,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m3","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.424242424242424,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m3","source":"aa-api","metric":"aa_ifbench","value":0.828571428571429,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m3","source":"aa-api","metric":"aa_long_context_reasoning","value":0.83,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m3","source":"aa-api","metric":"aa_tau2","value":0.888888888888889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-4.5","source":"aa-api","metric":"aa_math_index","value":91.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-4.5","source":"aa-api","metric":"aa_gpqa","value":0.866,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-4.5","source":"aa-api","metric":"aa_hle","value":0.301,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-4.5","source":"aa-api","metric":"aa_mmlu_pro","value":0.895,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-4.5","source":"aa-api","metric":"aa_livecodebench","value":0.871,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-4.5","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.46969696969697,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-4.5","source":"aa-api","metric":"aa_ifbench","value":0.579591836734694,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-4.5","source":"aa-api","metric":"aa_long_context_reasoning","value":0.773333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-4.5","source":"aa-api","metric":"aa_tau2","value":0.894736842105263,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-4.5","source":"aa-api","metric":"aa_aime_2025","value":0.913333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.2-codex","source":"aa-api","metric":"aa_gpqa","value":0.899,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.2-codex","source":"aa-api","metric":"aa_hle","value":0.357,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.2-codex","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.371212121212121,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.2-codex","source":"aa-api","metric":"aa_ifbench","value":0.776190476190476,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.2-codex","source":"aa-api","metric":"aa_long_context_reasoning","value":0.823333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.2-codex","source":"aa-api","metric":"aa_tau2","value":0.921052631578947,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5","source":"aa-api","metric":"aa_gpqa","value":0.82,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5","source":"aa-api","metric":"aa_hle","value":0.293,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.431818181818182,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5","source":"aa-api","metric":"aa_ifbench","value":0.72312925170068,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5","source":"aa-api","metric":"aa_long_context_reasoning","value":0.756666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5","source":"aa-api","metric":"aa_tau2","value":0.982456140350877,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.6-plus","source":"aa-api","metric":"aa_gpqa","value":0.882,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.6-plus","source":"aa-api","metric":"aa_hle","value":0.278,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.6-plus","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.439393939393939,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.6-plus","source":"aa-api","metric":"aa_ifbench","value":0.751700680272109,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.6-plus","source":"aa-api","metric":"aa_long_context_reasoning","value":0.783333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.6-plus","source":"aa-api","metric":"aa_tau2","value":0.976608187134503,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2.6","source":"aa-api","metric":"aa_gpqa","value":0.911,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2.6","source":"aa-api","metric":"aa_hle","value":0.375,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2.6","source":"aa-api","metric":"aa_scicode","value":0.515,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2.6","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.439393939393939,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2.6","source":"aa-api","metric":"aa_ifbench","value":0.759863945578231,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2.6","source":"aa-api","metric":"aa_long_context_reasoning","value":0.81,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2.6","source":"aa-api","metric":"aa_tau2","value":0.95906432748538,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5-turbo","source":"aa-api","metric":"aa_gpqa","value":0.847,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5-turbo","source":"aa-api","metric":"aa_hle","value":0.278,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5-turbo","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.333333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5-turbo","source":"aa-api","metric":"aa_ifbench","value":0.731972789115646,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5-turbo","source":"aa-api","metric":"aa_long_context_reasoning","value":0.716666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5-turbo","source":"aa-api","metric":"aa_tau2","value":0.985380116959064,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"upstage/solar-pro4","source":"aa-api","metric":"aa_gpqa","value":0.891,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"upstage/solar-pro4","source":"aa-api","metric":"aa_hle","value":0.298,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"upstage/solar-pro4","source":"aa-api","metric":"aa_scicode","value":0.48,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"upstage/solar-pro4","source":"aa-api","metric":"aa_long_context_reasoning","value":0.706666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"aa-api","metric":"aa_hle","value":0.307,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"aa-api","metric":"aa_scicode","value":0.478,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"aa-api","metric":"aa_long_context_reasoning","value":0.69,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3-flash-preview","source":"aa-api","metric":"aa_math_index","value":97,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3-flash-preview","source":"aa-api","metric":"aa_gpqa","value":0.898,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3-flash-preview","source":"aa-api","metric":"aa_hle","value":0.366,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3-flash-preview","source":"aa-api","metric":"aa_mmlu_pro","value":0.89,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3-flash-preview","source":"aa-api","metric":"aa_livecodebench","value":0.908,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3-flash-preview","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.386363636363636,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3-flash-preview","source":"aa-api","metric":"aa_ifbench","value":0.779591836734694,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3-flash-preview","source":"aa-api","metric":"aa_long_context_reasoning","value":0.78,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3-flash-preview","source":"aa-api","metric":"aa_tau2","value":0.804093567251462,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3-flash-preview","source":"aa-api","metric":"aa_aime_2025","value":0.97,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5.1","source":"aa-api","metric":"aa_gpqa","value":0.868,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5.1","source":"aa-api","metric":"aa_hle","value":0.301,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5.1","source":"aa-api","metric":"aa_scicode","value":0.448,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5.1","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.431818181818182,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5.1","source":"aa-api","metric":"aa_ifbench","value":0.762585034013605,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5.1","source":"aa-api","metric":"aa_long_context_reasoning","value":0.736666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5.1","source":"aa-api","metric":"aa_tau2","value":0.976608187134503,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"aa-api","metric":"aa_gpqa","value":0.866,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"aa-api","metric":"aa_hle","value":0.357,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"aa-api","metric":"aa_scicode","value":0.506,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.431818181818182,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"aa-api","metric":"aa_ifbench","value":0.798639455782313,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"aa-api","metric":"aa_long_context_reasoning","value":0.796666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"aa-api","metric":"aa_tau2","value":0.941520467836257,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2.7-code","source":"aa-api","metric":"aa_gpqa","value":0.896,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2.7-code","source":"aa-api","metric":"aa_hle","value":0.35,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2.7-code","source":"aa-api","metric":"aa_scicode","value":0.478,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2.7-code","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.446969696969697,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2.7-code","source":"aa-api","metric":"aa_ifbench","value":0.631292517006803,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2.7-code","source":"aa-api","metric":"aa_long_context_reasoning","value":0.793333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2.7-code","source":"aa-api","metric":"aa_tau2","value":0.900584795321637,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"thinkingmachines/inkling-small","source":"aa-api","metric":"aa_gpqa","value":0.895,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"thinkingmachines/inkling-small","source":"aa-api","metric":"aa_hle","value":0.333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"thinkingmachines/inkling-small","source":"aa-api","metric":"aa_scicode","value":0.497,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"thinkingmachines/inkling-small","source":"aa-api","metric":"aa_long_context_reasoning","value":0.756666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"x-ai/grok-4.20","source":"aa-api","metric":"aa_gpqa","value":0.911,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"x-ai/grok-4.20","source":"aa-api","metric":"aa_hle","value":0.345,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"x-ai/grok-4.20","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.378787878787879,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"x-ai/grok-4.20","source":"aa-api","metric":"aa_ifbench","value":0.812244897959184,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"x-ai/grok-4.20","source":"aa-api","metric":"aa_long_context_reasoning","value":0.69,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"x-ai/grok-4.20","source":"aa-api","metric":"aa_tau2","value":0.929824561403509,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"tencent/hy3","source":"aa-api","metric":"aa_gpqa","value":0.897,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"tencent/hy3","source":"aa-api","metric":"aa_hle","value":0.335,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"tencent/hy3","source":"aa-api","metric":"aa_scicode","value":0.486,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"tencent/hy3","source":"aa-api","metric":"aa_long_context_reasoning","value":0.79,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.7-plus","source":"aa-api","metric":"aa_gpqa","value":0.9,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.7-plus","source":"aa-api","metric":"aa_hle","value":0.356,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.7-plus","source":"aa-api","metric":"aa_scicode","value":0.461,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.7-plus","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.46969696969697,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.7-plus","source":"aa-api","metric":"aa_ifbench","value":0.779591836734694,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.7-plus","source":"aa-api","metric":"aa_long_context_reasoning","value":0.73,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.7-plus","source":"aa-api","metric":"aa_tau2","value":0.929824561403509,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"thinkingmachines/inkling","source":"aa-api","metric":"aa_gpqa","value":0.872,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"thinkingmachines/inkling","source":"aa-api","metric":"aa_hle","value":0.319,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"thinkingmachines/inkling","source":"aa-api","metric":"aa_scicode","value":0.47,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"thinkingmachines/inkling","source":"aa-api","metric":"aa_long_context_reasoning","value":0.773333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"x-ai/grok-4.3","source":"aa-api","metric":"aa_gpqa","value":0.901,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"x-ai/grok-4.3","source":"aa-api","metric":"aa_hle","value":0.372,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"x-ai/grok-4.3","source":"aa-api","metric":"aa_scicode","value":0.483,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"x-ai/grok-4.3","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.378787878787879,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"x-ai/grok-4.3","source":"aa-api","metric":"aa_ifbench","value":0.833333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"x-ai/grok-4.3","source":"aa-api","metric":"aa_long_context_reasoning","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"x-ai/grok-4.3","source":"aa-api","metric":"aa_tau2","value":0.976608187134503,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.1","source":"aa-api","metric":"aa_math_index","value":94,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.1","source":"aa-api","metric":"aa_gpqa","value":0.873,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.1","source":"aa-api","metric":"aa_hle","value":0.285,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.1","source":"aa-api","metric":"aa_mmlu_pro","value":0.87,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.1","source":"aa-api","metric":"aa_livecodebench","value":0.868,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.1","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.454545454545455,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.1","source":"aa-api","metric":"aa_ifbench","value":0.728571428571429,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.1","source":"aa-api","metric":"aa_long_context_reasoning","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.1","source":"aa-api","metric":"aa_tau2","value":0.818713450292398,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.1","source":"aa-api","metric":"aa_aime_2025","value":0.94,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"inclusionai/ling-3.0-flash-vl","source":"aa-api","metric":"aa_gpqa","value":0.862,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"inclusionai/ling-3.0-flash-vl","source":"aa-api","metric":"aa_hle","value":0.22,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"inclusionai/ling-3.0-flash-vl","source":"aa-api","metric":"aa_scicode","value":0.442,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"inclusionai/ling-3.0-flash-vl","source":"aa-api","metric":"aa_long_context_reasoning","value":0.783333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.4-mini","source":"aa-api","metric":"aa_gpqa","value":0.875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.4-mini","source":"aa-api","metric":"aa_hle","value":0.281,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.4-mini","source":"aa-api","metric":"aa_scicode","value":0.521,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.4-mini","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.522727272727273,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.4-mini","source":"aa-api","metric":"aa_ifbench","value":0.73265306122449,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.4-mini","source":"aa-api","metric":"aa_long_context_reasoning","value":0.77,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.4-mini","source":"aa-api","metric":"aa_tau2","value":0.833333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"upstage/solar-mini4","source":"aa-api","metric":"aa_hle","value":0.258,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"upstage/solar-mini4","source":"aa-api","metric":"aa_scicode","value":0.476,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"upstage/solar-mini4","source":"aa-api","metric":"aa_long_context_reasoning","value":0.833333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.1-codex","source":"aa-api","metric":"aa_math_index","value":95.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.1-codex","source":"aa-api","metric":"aa_gpqa","value":0.86,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.1-codex","source":"aa-api","metric":"aa_hle","value":0.257,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.1-codex","source":"aa-api","metric":"aa_mmlu_pro","value":0.86,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.1-codex","source":"aa-api","metric":"aa_livecodebench","value":0.849,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.1-codex","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.348484848484849,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.1-codex","source":"aa-api","metric":"aa_ifbench","value":0.7,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.1-codex","source":"aa-api","metric":"aa_long_context_reasoning","value":0.693333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.1-codex","source":"aa-api","metric":"aa_tau2","value":0.830409356725146,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.1-codex","source":"aa-api","metric":"aa_aime_2025","value":0.956666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5v-turbo","source":"aa-api","metric":"aa_gpqa","value":0.809,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5v-turbo","source":"aa-api","metric":"aa_hle","value":0.171,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5v-turbo","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.325757575757576,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5v-turbo","source":"aa-api","metric":"aa_ifbench","value":0.610884353741497,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5v-turbo","source":"aa-api","metric":"aa_long_context_reasoning","value":0.703333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5v-turbo","source":"aa-api","metric":"aa_tau2","value":0.985380116959064,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2.5","source":"aa-api","metric":"aa_gpqa","value":0.879,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2.5","source":"aa-api","metric":"aa_hle","value":0.307,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2.5","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.348484848484849,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2.5","source":"aa-api","metric":"aa_ifbench","value":0.702040816326531,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2.5","source":"aa-api","metric":"aa_long_context_reasoning","value":0.78,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2.5","source":"aa-api","metric":"aa_tau2","value":0.95906432748538,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5","source":"aa-api","metric":"aa_math_index","value":94.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5","source":"aa-api","metric":"aa_gpqa","value":0.854,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5","source":"aa-api","metric":"aa_hle","value":0.285,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5","source":"aa-api","metric":"aa_mmlu_pro","value":0.871,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5","source":"aa-api","metric":"aa_livecodebench","value":0.846,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.378787878787879,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5","source":"aa-api","metric":"aa_ifbench","value":0.730612244897959,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5","source":"aa-api","metric":"aa_long_context_reasoning","value":0.782,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5","source":"aa-api","metric":"aa_tau2","value":0.865497076023392,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5","source":"aa-api","metric":"aa_aime_2025","value":0.943333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"aa-api","metric":"aa_gpqa","value":0.867,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"aa-api","metric":"aa_hle","value":0.284,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"aa-api","metric":"aa_scicode","value":0.403,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.363636363636364,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"aa-api","metric":"aa_ifbench","value":0.813605442176871,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"aa-api","metric":"aa_long_context_reasoning","value":0.793333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"aa-api","metric":"aa_tau2","value":0.833333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.5-27b","source":"aa-api","metric":"aa_gpqa","value":0.858,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.5-27b","source":"aa-api","metric":"aa_hle","value":0.239,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.5-27b","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.325757575757576,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.5-27b","source":"aa-api","metric":"aa_ifbench","value":0.75578231292517,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.5-27b","source":"aa-api","metric":"aa_long_context_reasoning","value":0.776666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.5-27b","source":"aa-api","metric":"aa_tau2","value":0.93859649122807,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m2.5","source":"aa-api","metric":"aa_gpqa","value":0.848,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m2.5","source":"aa-api","metric":"aa_hle","value":0.205,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m2.5","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.348484848484849,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m2.5","source":"aa-api","metric":"aa_ifbench","value":0.716326530612245,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m2.5","source":"aa-api","metric":"aa_long_context_reasoning","value":0.733333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m2.5","source":"aa-api","metric":"aa_tau2","value":0.953216374269006,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m2.7","source":"aa-api","metric":"aa_gpqa","value":0.874,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m2.7","source":"aa-api","metric":"aa_hle","value":0.296,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m2.7","source":"aa-api","metric":"aa_scicode","value":0.501,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m2.7","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.393939393939394,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m2.7","source":"aa-api","metric":"aa_ifbench","value":0.757142857142857,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m2.7","source":"aa-api","metric":"aa_long_context_reasoning","value":0.783333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m2.7","source":"aa-api","metric":"aa_tau2","value":0.847953216374269,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"tencent/hy3-preview","source":"aa-api","metric":"aa_gpqa","value":0.867,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"tencent/hy3-preview","source":"aa-api","metric":"aa_hle","value":0.278,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"tencent/hy3-preview","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.340909090909091,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"tencent/hy3-preview","source":"aa-api","metric":"aa_ifbench","value":0.631292517006803,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"tencent/hy3-preview","source":"aa-api","metric":"aa_long_context_reasoning","value":0.646666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"tencent/hy3-preview","source":"aa-api","metric":"aa_tau2","value":0.926900584795322,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.7","source":"aa-api","metric":"aa_math_index","value":95,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.7","source":"aa-api","metric":"aa_gpqa","value":0.859,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.7","source":"aa-api","metric":"aa_hle","value":0.274,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.7","source":"aa-api","metric":"aa_mmlu_pro","value":0.856,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.7","source":"aa-api","metric":"aa_livecodebench","value":0.894,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.7","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.318181818181818,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.7","source":"aa-api","metric":"aa_ifbench","value":0.67891156462585,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.7","source":"aa-api","metric":"aa_long_context_reasoning","value":0.71,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.7","source":"aa-api","metric":"aa_tau2","value":0.95906432748538,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.7","source":"aa-api","metric":"aa_aime_2025","value":0.95,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.5-flash-lite","source":"aa-api","metric":"aa_gpqa","value":0.838,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.5-flash-lite","source":"aa-api","metric":"aa_hle","value":0.188,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.5-flash-lite","source":"aa-api","metric":"aa_scicode","value":0.413,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.5-flash-lite","source":"aa-api","metric":"aa_long_context_reasoning","value":0.76,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2-thinking","source":"aa-api","metric":"aa_math_index","value":94.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2-thinking","source":"aa-api","metric":"aa_gpqa","value":0.838,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2-thinking","source":"aa-api","metric":"aa_hle","value":0.238,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2-thinking","source":"aa-api","metric":"aa_mmlu_pro","value":0.848,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2-thinking","source":"aa-api","metric":"aa_livecodebench","value":0.853,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2-thinking","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.310606060606061,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2-thinking","source":"aa-api","metric":"aa_ifbench","value":0.680952380952381,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2-thinking","source":"aa-api","metric":"aa_long_context_reasoning","value":0.72,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2-thinking","source":"aa-api","metric":"aa_tau2","value":0.929824561403509,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2-thinking","source":"aa-api","metric":"aa_aime_2025","value":0.946666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o3-pro","source":"aa-api","metric":"aa_gpqa","value":0.845,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"xiaomi/mimo-v2.5","source":"aa-api","metric":"aa_gpqa","value":0.849,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"xiaomi/mimo-v2.5","source":"aa-api","metric":"aa_hle","value":0.272,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"xiaomi/mimo-v2.5","source":"aa-api","metric":"aa_scicode","value":0.439,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"xiaomi/mimo-v2.5","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.416666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"xiaomi/mimo-v2.5","source":"aa-api","metric":"aa_ifbench","value":0.671428571428571,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"xiaomi/mimo-v2.5","source":"aa-api","metric":"aa_long_context_reasoning","value":0.73,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"xiaomi/mimo-v2.5","source":"aa-api","metric":"aa_tau2","value":0.906432748538012,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v3.2","source":"aa-api","metric":"aa_math_index","value":92,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v3.2","source":"aa-api","metric":"aa_gpqa","value":0.84,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v3.2","source":"aa-api","metric":"aa_hle","value":0.246,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v3.2","source":"aa-api","metric":"aa_mmlu_pro","value":0.862,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v3.2","source":"aa-api","metric":"aa_livecodebench","value":0.862,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v3.2","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.356060606060606,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v3.2","source":"aa-api","metric":"aa_ifbench","value":0.606802721088435,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v3.2","source":"aa-api","metric":"aa_long_context_reasoning","value":0.733333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v3.2","source":"aa-api","metric":"aa_tau2","value":0.906432748538012,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v3.2","source":"aa-api","metric":"aa_aime_2025","value":0.92,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"aa-api","metric":"aa_gpqa","value":0.893,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"aa-api","metric":"aa_hle","value":0.29,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.409090909090909,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"aa-api","metric":"aa_ifbench","value":0.787755102040816,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"aa-api","metric":"aa_long_context_reasoning","value":0.773333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"aa-api","metric":"aa_tau2","value":0.956140350877193,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.6-27b","source":"aa-api","metric":"aa_gpqa","value":0.842,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.6-27b","source":"aa-api","metric":"aa_hle","value":0.231,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.6-27b","source":"aa-api","metric":"aa_scicode","value":0.428,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.6-27b","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.348484848484849,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.6-27b","source":"aa-api","metric":"aa_ifbench","value":0.675510204081633,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.6-27b","source":"aa-api","metric":"aa_long_context_reasoning","value":0.773333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.6-27b","source":"aa-api","metric":"aa_tau2","value":0.941520467836257,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m2.1","source":"aa-api","metric":"aa_math_index","value":82.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m2.1","source":"aa-api","metric":"aa_gpqa","value":0.83,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m2.1","source":"aa-api","metric":"aa_hle","value":0.232,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m2.1","source":"aa-api","metric":"aa_mmlu_pro","value":0.875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m2.1","source":"aa-api","metric":"aa_livecodebench","value":0.81,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m2.1","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.287878787878788,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m2.1","source":"aa-api","metric":"aa_ifbench","value":0.698639455782313,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m2.1","source":"aa-api","metric":"aa_long_context_reasoning","value":0.676666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m2.1","source":"aa-api","metric":"aa_tau2","value":0.853801169590643,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m2.1","source":"aa-api","metric":"aa_aime_2025","value":0.826666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.4-nano","source":"aa-api","metric":"aa_gpqa","value":0.817,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.4-nano","source":"aa-api","metric":"aa_hle","value":0.283,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.4-nano","source":"aa-api","metric":"aa_scicode","value":0.472,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.4-nano","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.424242424242424,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.4-nano","source":"aa-api","metric":"aa_ifbench","value":0.759183673469388,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.4-nano","source":"aa-api","metric":"aa_long_context_reasoning","value":0.766666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.4-nano","source":"aa-api","metric":"aa_tau2","value":0.760233918128655,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5-mini","source":"aa-api","metric":"aa_math_index","value":90.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5-mini","source":"aa-api","metric":"aa_gpqa","value":0.828,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5-mini","source":"aa-api","metric":"aa_hle","value":0.215,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5-mini","source":"aa-api","metric":"aa_mmlu_pro","value":0.837,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5-mini","source":"aa-api","metric":"aa_livecodebench","value":0.838,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5-mini","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.333333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5-mini","source":"aa-api","metric":"aa_ifbench","value":0.754421768707483,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5-mini","source":"aa-api","metric":"aa_long_context_reasoning","value":0.723333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5-mini","source":"aa-api","metric":"aa_tau2","value":0.710526315789474,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5-mini","source":"aa-api","metric":"aa_aime_2025","value":0.906666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.1-codex-mini","source":"aa-api","metric":"aa_math_index","value":91.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.1-codex-mini","source":"aa-api","metric":"aa_gpqa","value":0.813,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.1-codex-mini","source":"aa-api","metric":"aa_hle","value":0.185,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.1-codex-mini","source":"aa-api","metric":"aa_mmlu_pro","value":0.82,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.1-codex-mini","source":"aa-api","metric":"aa_livecodebench","value":0.836,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.1-codex-mini","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.333333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.1-codex-mini","source":"aa-api","metric":"aa_ifbench","value":0.67891156462585,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.1-codex-mini","source":"aa-api","metric":"aa_long_context_reasoning","value":0.666666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.1-codex-mini","source":"aa-api","metric":"aa_tau2","value":0.628654970760234,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5.1-codex-mini","source":"aa-api","metric":"aa_aime_2025","value":0.916666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o3","source":"aa-api","metric":"aa_math_index","value":88.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o3","source":"aa-api","metric":"aa_gpqa","value":0.827,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o3","source":"aa-api","metric":"aa_hle","value":0.201,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o3","source":"aa-api","metric":"aa_mmlu_pro","value":0.853,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o3","source":"aa-api","metric":"aa_livecodebench","value":0.808,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o3","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.371212121212121,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o3","source":"aa-api","metric":"aa_ifbench","value":0.714285714285714,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o3","source":"aa-api","metric":"aa_long_context_reasoning","value":0.746666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o3","source":"aa-api","metric":"aa_tau2","value":0.807017543859649,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o3","source":"aa-api","metric":"aa_aime_2025","value":0.883333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"inclusionai/ling-3.0-flash","source":"aa-api","metric":"aa_gpqa","value":0.855,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"inclusionai/ling-3.0-flash","source":"aa-api","metric":"aa_hle","value":0.237,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"inclusionai/ling-3.0-flash","source":"aa-api","metric":"aa_scicode","value":0.42,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"inclusionai/ling-3.0-flash","source":"aa-api","metric":"aa_long_context_reasoning","value":0.73,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"stepfun/step-3.7-flash","source":"aa-api","metric":"aa_gpqa","value":0.809,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"stepfun/step-3.7-flash","source":"aa-api","metric":"aa_hle","value":0.214,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"stepfun/step-3.7-flash","source":"aa-api","metric":"aa_scicode","value":0.439,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"stepfun/step-3.7-flash","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.356060606060606,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"stepfun/step-3.7-flash","source":"aa-api","metric":"aa_ifbench","value":0.672789115646258,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"stepfun/step-3.7-flash","source":"aa-api","metric":"aa_long_context_reasoning","value":0.736666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"stepfun/step-3.7-flash","source":"aa-api","metric":"aa_tau2","value":0.985380116959064,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"aa-api","metric":"aa_gpqa","value":0.845,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"aa-api","metric":"aa_hle","value":0.21,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.265151515151515,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"aa-api","metric":"aa_ifbench","value":0.725170068027211,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"aa-api","metric":"aa_long_context_reasoning","value":0.72,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"aa-api","metric":"aa_tau2","value":0.891812865497076,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meituan/longcat-2.0","source":"aa-api","metric":"aa_gpqa","value":0.78,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meituan/longcat-2.0","source":"aa-api","metric":"aa_hle","value":0.337,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meituan/longcat-2.0","source":"aa-api","metric":"aa_scicode","value":0.363,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meituan/longcat-2.0","source":"aa-api","metric":"aa_long_context_reasoning","value":0.65,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m2","source":"aa-api","metric":"aa_math_index","value":78.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m2","source":"aa-api","metric":"aa_gpqa","value":0.777,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m2","source":"aa-api","metric":"aa_hle","value":0.137,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m2","source":"aa-api","metric":"aa_mmlu_pro","value":0.82,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m2","source":"aa-api","metric":"aa_livecodebench","value":0.826,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m2","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.257575757575758,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m2","source":"aa-api","metric":"aa_ifbench","value":0.72312925170068,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m2","source":"aa-api","metric":"aa_long_context_reasoning","value":0.643333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m2","source":"aa-api","metric":"aa_tau2","value":0.868421052631579,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m2","source":"aa-api","metric":"aa_aime_2025","value":0.783333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.6","source":"aa-api","metric":"aa_math_index","value":86,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.6","source":"aa-api","metric":"aa_gpqa","value":0.78,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.6","source":"aa-api","metric":"aa_hle","value":0.145,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.6","source":"aa-api","metric":"aa_mmlu_pro","value":0.829,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.6","source":"aa-api","metric":"aa_livecodebench","value":0.695,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.6","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.287878787878788,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.6","source":"aa-api","metric":"aa_ifbench","value":0.434013605442177,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.6","source":"aa-api","metric":"aa_long_context_reasoning","value":0.54,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.6","source":"aa-api","metric":"aa_tau2","value":0.769005847953216,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.6","source":"aa-api","metric":"aa_aime_2025","value":0.86,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"aa-api","metric":"aa_scicode","value":0.448,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.6-35b-a3b","source":"aa-api","metric":"aa_gpqa","value":0.841,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.6-35b-a3b","source":"aa-api","metric":"aa_hle","value":0.222,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.6-35b-a3b","source":"aa-api","metric":"aa_scicode","value":0.366,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.6-35b-a3b","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.348484848484849,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.6-35b-a3b","source":"aa-api","metric":"aa_ifbench","value":0.643537414965986,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.6-35b-a3b","source":"aa-api","metric":"aa_long_context_reasoning","value":0.716666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.6-35b-a3b","source":"aa-api","metric":"aa_tau2","value":0.953216374269006,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"aa-api","metric":"aa_gpqa","value":0.857,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"aa-api","metric":"aa_hle","value":0.252,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.310606060606061,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"aa-api","metric":"aa_ifbench","value":0.757142857142857,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"aa-api","metric":"aa_long_context_reasoning","value":0.763333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"aa-api","metric":"aa_tau2","value":0.935672514619883,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"stepfun/step-3.5-flash","source":"aa-api","metric":"aa_gpqa","value":0.831,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"stepfun/step-3.5-flash","source":"aa-api","metric":"aa_hle","value":0.245,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"stepfun/step-3.5-flash","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.325757575757576,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"stepfun/step-3.5-flash","source":"aa-api","metric":"aa_ifbench","value":0.66530612244898,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"stepfun/step-3.5-flash","source":"aa-api","metric":"aa_long_context_reasoning","value":0.63,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"stepfun/step-3.5-flash","source":"aa-api","metric":"aa_tau2","value":0.944444444444444,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5-mini","source":"aa-api","metric":"aa_scicode","value":0.39,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-4-26b-a4b-it","source":"aa-api","metric":"aa_gpqa","value":0.792,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-4-26b-a4b-it","source":"aa-api","metric":"aa_hle","value":0.193,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-4-26b-a4b-it","source":"aa-api","metric":"aa_scicode","value":0.4,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-4-26b-a4b-it","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.25,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-4-26b-a4b-it","source":"aa-api","metric":"aa_ifbench","value":0.724489795918367,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-4-26b-a4b-it","source":"aa-api","metric":"aa_long_context_reasoning","value":0.656666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-4-26b-a4b-it","source":"aa-api","metric":"aa_tau2","value":0.435672514619883,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o4-mini","source":"aa-api","metric":"aa_math_index","value":90.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o4-mini","source":"aa-api","metric":"aa_gpqa","value":0.784,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o4-mini","source":"aa-api","metric":"aa_hle","value":0.165,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o4-mini","source":"aa-api","metric":"aa_mmlu_pro","value":0.832,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o4-mini","source":"aa-api","metric":"aa_livecodebench","value":0.859,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o4-mini","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.151515151515152,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o4-mini","source":"aa-api","metric":"aa_ifbench","value":0.687074829931973,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o4-mini","source":"aa-api","metric":"aa_long_context_reasoning","value":0.61,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o4-mini","source":"aa-api","metric":"aa_tau2","value":0.555555555555556,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o4-mini","source":"aa-api","metric":"aa_aime_2025","value":0.906666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"aa-api","metric":"aa_math_index","value":87.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"aa-api","metric":"aa_gpqa","value":0.797,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"aa-api","metric":"aa_hle","value":0.149,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"aa-api","metric":"aa_mmlu_pro","value":0.85,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"aa-api","metric":"aa_livecodebench","value":0.789,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.310606060606061,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"aa-api","metric":"aa_ifbench","value":0.541496598639456,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"aa-api","metric":"aa_long_context_reasoning","value":0.723333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"aa-api","metric":"aa_tau2","value":0.339181286549708,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"aa-api","metric":"aa_aime_2025","value":0.876666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-2.5-pro","source":"aa-api","metric":"aa_math_index","value":87.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-2.5-pro","source":"aa-api","metric":"aa_gpqa","value":0.844,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-2.5-pro","source":"aa-api","metric":"aa_hle","value":0.225,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-2.5-pro","source":"aa-api","metric":"aa_mmlu_pro","value":0.862,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-2.5-pro","source":"aa-api","metric":"aa_livecodebench","value":0.801,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-2.5-pro","source":"aa-api","metric":"aa_scicode","value":0.463,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-2.5-pro","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.265151515151515,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-2.5-pro","source":"aa-api","metric":"aa_ifbench","value":0.487074829931973,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-2.5-pro","source":"aa-api","metric":"aa_long_context_reasoning","value":0.69,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-2.5-pro","source":"aa-api","metric":"aa_tau2","value":0.54093567251462,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-2.5-pro","source":"aa-api","metric":"aa_aime_2025","value":0.876666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"aa-api","metric":"aa_scicode","value":0.397,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.1-flash-lite","source":"aa-api","metric":"aa_gpqa","value":0.822,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.1-flash-lite","source":"aa-api","metric":"aa_hle","value":0.172,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.1-flash-lite","source":"aa-api","metric":"aa_scicode","value":0.434,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.1-flash-lite","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.242424242424242,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.1-flash-lite","source":"aa-api","metric":"aa_ifbench","value":0.772108843537415,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.1-flash-lite","source":"aa-api","metric":"aa_long_context_reasoning","value":0.743333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.1-flash-lite","source":"aa-api","metric":"aa_tau2","value":0.312865497076023,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2-0905","source":"aa-api","metric":"aa_math_index","value":57.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2-0905","source":"aa-api","metric":"aa_gpqa","value":0.767,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2-0905","source":"aa-api","metric":"aa_hle","value":0.064,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2-0905","source":"aa-api","metric":"aa_mmlu_pro","value":0.819,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2-0905","source":"aa-api","metric":"aa_livecodebench","value":0.61,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2-0905","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.234848484848485,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2-0905","source":"aa-api","metric":"aa_ifbench","value":0.417006802721088,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2-0905","source":"aa-api","metric":"aa_long_context_reasoning","value":0.53,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2-0905","source":"aa-api","metric":"aa_tau2","value":0.733918128654971,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2-0905","source":"aa-api","metric":"aa_aime_2025","value":0.573333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o1","source":"aa-api","metric":"aa_gpqa","value":0.747,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o1","source":"aa-api","metric":"aa_hle","value":0.07,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o1","source":"aa-api","metric":"aa_mmlu_pro","value":0.841,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o1","source":"aa-api","metric":"aa_livecodebench","value":0.679,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o1","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.128787878787879,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o1","source":"aa-api","metric":"aa_ifbench","value":0.703401360544218,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o1","source":"aa-api","metric":"aa_long_context_reasoning","value":0.65,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o1","source":"aa-api","metric":"aa_tau2","value":0.625730994152047,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-2.5-pro-preview","source":"aa-api","metric":"aa_gpqa","value":0.836,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-2.5-pro-preview","source":"aa-api","metric":"aa_hle","value":0.199,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-2.5-pro-preview","source":"aa-api","metric":"aa_mmlu_pro","value":0.858,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-2.5-pro-preview","source":"aa-api","metric":"aa_livecodebench","value":0.778,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.7-flash","source":"aa-api","metric":"aa_gpqa","value":0.581,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.7-flash","source":"aa-api","metric":"aa_hle","value":0.076,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.7-flash","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.21969696969697,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.7-flash","source":"aa-api","metric":"aa_ifbench","value":0.608163265306122,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.7-flash","source":"aa-api","metric":"aa_long_context_reasoning","value":0.416666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.7-flash","source":"aa-api","metric":"aa_tau2","value":0.988304093567251,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"aa-api","metric":"aa_math_index","value":89.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"aa-api","metric":"aa_gpqa","value":0.792,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"aa-api","metric":"aa_hle","value":0.164,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"aa-api","metric":"aa_mmlu_pro","value":0.851,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"aa-api","metric":"aa_livecodebench","value":0.798,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"aa-api","metric":"aa_scicode","value":0.38,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.318181818181818,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"aa-api","metric":"aa_ifbench","value":0.570068027210884,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"aa-api","metric":"aa_long_context_reasoning","value":0.693333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"aa-api","metric":"aa_tau2","value":0.371345029239766,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"aa-api","metric":"aa_aime_2025","value":0.896666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-4-31b-it","source":"aa-api","metric":"aa_gpqa","value":0.857,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-4-31b-it","source":"aa-api","metric":"aa_hle","value":0.236,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-4-31b-it","source":"aa-api","metric":"aa_scicode","value":0.455,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-4-31b-it","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.363636363636364,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-4-31b-it","source":"aa-api","metric":"aa_ifbench","value":0.75578231292517,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-4-31b-it","source":"aa-api","metric":"aa_long_context_reasoning","value":0.696666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-4-31b-it","source":"aa-api","metric":"aa_tau2","value":0.654970760233918,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-medium-3-5","source":"aa-api","metric":"aa_gpqa","value":0.748,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-medium-3-5","source":"aa-api","metric":"aa_hle","value":0.138,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-medium-3-5","source":"aa-api","metric":"aa_scicode","value":0.402,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-medium-3-5","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.333333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-medium-3-5","source":"aa-api","metric":"aa_ifbench","value":0.687755102040816,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-medium-3-5","source":"aa-api","metric":"aa_long_context_reasoning","value":0.693333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-medium-3-5","source":"aa-api","metric":"aa_tau2","value":0.941520467836257,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"aa-api","metric":"aa_math_index","value":88.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"aa-api","metric":"aa_gpqa","value":0.772,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"aa-api","metric":"aa_hle","value":0.119,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"aa-api","metric":"aa_mmlu_pro","value":0.836,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"aa-api","metric":"aa_livecodebench","value":0.646,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.113636363636364,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"aa-api","metric":"aa_ifbench","value":0.564625850340136,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"aa-api","metric":"aa_long_context_reasoning","value":0.636666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"aa-api","metric":"aa_tau2","value":0.54093567251462,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"aa-api","metric":"aa_aime_2025","value":0.883333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.5-9b","source":"aa-api","metric":"aa_gpqa","value":0.806,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.5-9b","source":"aa-api","metric":"aa_hle","value":0.149,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.5-9b","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.242424242424242,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.5-9b","source":"aa-api","metric":"aa_ifbench","value":0.66734693877551,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.5-9b","source":"aa-api","metric":"aa_long_context_reasoning","value":0.7,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.5-9b","source":"aa-api","metric":"aa_tau2","value":0.868421052631579,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"cohere/command-a","source":"aa-api","metric":"aa_gpqa","value":0.761,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"cohere/command-a","source":"aa-api","metric":"aa_hle","value":0.12,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"cohere/command-a","source":"aa-api","metric":"aa_scicode","value":0.385,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"cohere/command-a","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.25,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"cohere/command-a","source":"aa-api","metric":"aa_ifbench","value":0.739455782312925,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"cohere/command-a","source":"aa-api","metric":"aa_long_context_reasoning","value":0.526666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"cohere/command-a","source":"aa-api","metric":"aa_tau2","value":0.807017543859649,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-r1-0528","source":"aa-api","metric":"aa_math_index","value":76,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-r1-0528","source":"aa-api","metric":"aa_gpqa","value":0.813,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-r1-0528","source":"aa-api","metric":"aa_hle","value":0.158,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-r1-0528","source":"aa-api","metric":"aa_mmlu_pro","value":0.849,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-r1-0528","source":"aa-api","metric":"aa_livecodebench","value":0.77,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-r1-0528","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.159090909090909,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-r1-0528","source":"aa-api","metric":"aa_ifbench","value":0.395918367346939,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-r1-0528","source":"aa-api","metric":"aa_long_context_reasoning","value":0.556666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-r1-0528","source":"aa-api","metric":"aa_tau2","value":0.365497076023392,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-r1-0528","source":"aa-api","metric":"aa_aime_2025","value":0.76,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-2.5-flash","source":"aa-api","metric":"aa_math_index","value":73.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-2.5-flash","source":"aa-api","metric":"aa_gpqa","value":0.79,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-2.5-flash","source":"aa-api","metric":"aa_hle","value":0.121,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-2.5-flash","source":"aa-api","metric":"aa_mmlu_pro","value":0.832,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-2.5-flash","source":"aa-api","metric":"aa_livecodebench","value":0.695,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-2.5-flash","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.136363636363636,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-2.5-flash","source":"aa-api","metric":"aa_ifbench","value":0.502721088435374,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-2.5-flash","source":"aa-api","metric":"aa_long_context_reasoning","value":0.653333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-2.5-flash","source":"aa-api","metric":"aa_tau2","value":0.315789473684211,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-2.5-flash","source":"aa-api","metric":"aa_aime_2025","value":0.733333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5-nano","source":"aa-api","metric":"aa_math_index","value":83.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5-nano","source":"aa-api","metric":"aa_gpqa","value":0.676,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5-nano","source":"aa-api","metric":"aa_hle","value":0.095,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5-nano","source":"aa-api","metric":"aa_mmlu_pro","value":0.78,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5-nano","source":"aa-api","metric":"aa_livecodebench","value":0.789,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5-nano","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.174242424242424,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5-nano","source":"aa-api","metric":"aa_ifbench","value":0.675510204081633,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5-nano","source":"aa-api","metric":"aa_long_context_reasoning","value":0.45,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5-nano","source":"aa-api","metric":"aa_tau2","value":0.365497076023392,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-5-nano","source":"aa-api","metric":"aa_aime_2025","value":0.836666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"aa-api","metric":"aa_gpqa","value":0.743,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"aa-api","metric":"aa_hle","value":0.106,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"aa-api","metric":"aa_scicode","value":0.321,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"aa-api","metric":"aa_long_context_reasoning","value":0.603333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"aa-api","metric":"aa_gpqa","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"aa-api","metric":"aa_hle","value":0.208,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"aa-api","metric":"aa_scicode","value":0.362,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.287878787878788,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"aa-api","metric":"aa_ifbench","value":0.714965986394558,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"aa-api","metric":"aa_long_context_reasoning","value":0.656666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"aa-api","metric":"aa_tau2","value":0.678362573099415,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.5","source":"aa-api","metric":"aa_math_index","value":73.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.5","source":"aa-api","metric":"aa_gpqa","value":0.782,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.5","source":"aa-api","metric":"aa_hle","value":0.13,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.5","source":"aa-api","metric":"aa_mmlu_pro","value":0.835,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.5","source":"aa-api","metric":"aa_livecodebench","value":0.738,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.5","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.21969696969697,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.5","source":"aa-api","metric":"aa_ifbench","value":0.440816326530612,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.5","source":"aa-api","metric":"aa_long_context_reasoning","value":0.526666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.5","source":"aa-api","metric":"aa_tau2","value":0.429824561403509,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.5","source":"aa-api","metric":"aa_aime_2025","value":0.736666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2","source":"aa-api","metric":"aa_math_index","value":57,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2","source":"aa-api","metric":"aa_gpqa","value":0.766,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2","source":"aa-api","metric":"aa_hle","value":0.074,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2","source":"aa-api","metric":"aa_mmlu_pro","value":0.824,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2","source":"aa-api","metric":"aa_livecodebench","value":0.556,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.159090909090909,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2","source":"aa-api","metric":"aa_ifbench","value":0.414965986394558,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2","source":"aa-api","metric":"aa_long_context_reasoning","value":0.53,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2","source":"aa-api","metric":"aa_tau2","value":0.611111111111111,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2","source":"aa-api","metric":"aa_aime_2025","value":0.57,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"aa-api","metric":"aa_math_index","value":91,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"aa-api","metric":"aa_gpqa","value":0.79,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"aa-api","metric":"aa_hle","value":0.159,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"aa-api","metric":"aa_mmlu_pro","value":0.843,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"aa-api","metric":"aa_livecodebench","value":0.788,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"aa-api","metric":"aa_scicode","value":0.414,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.151515151515152,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"aa-api","metric":"aa_ifbench","value":0.512244897959184,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"aa-api","metric":"aa_long_context_reasoning","value":0.72,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"aa-api","metric":"aa_tau2","value":0.532163742690059,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"aa-api","metric":"aa_aime_2025","value":0.91,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4.1","source":"aa-api","metric":"aa_math_index","value":34.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4.1","source":"aa-api","metric":"aa_gpqa","value":0.666,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4.1","source":"aa-api","metric":"aa_hle","value":0.042,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4.1","source":"aa-api","metric":"aa_mmlu_pro","value":0.806,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4.1","source":"aa-api","metric":"aa_livecodebench","value":0.457,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4.1","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.136363636363636,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4.1","source":"aa-api","metric":"aa_ifbench","value":0.429931972789116,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4.1","source":"aa-api","metric":"aa_long_context_reasoning","value":0.683333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4.1","source":"aa-api","metric":"aa_tau2","value":0.470760233918129,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4.1","source":"aa-api","metric":"aa_aime_2025","value":0.346666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o3-mini","source":"aa-api","metric":"aa_gpqa","value":0.773,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o3-mini","source":"aa-api","metric":"aa_hle","value":0.12,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o3-mini","source":"aa-api","metric":"aa_mmlu_pro","value":0.802,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o3-mini","source":"aa-api","metric":"aa_livecodebench","value":0.734,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o3-mini","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.0681818181818182,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o3-mini","source":"aa-api","metric":"aa_tau2","value":0.312865497076023,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"inception/mercury-2.5","source":"aa-api","metric":"aa_hle","value":0.118,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"inception/mercury-2.5","source":"aa-api","metric":"aa_scicode","value":0.385,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"inception/mercury-2.5","source":"aa-api","metric":"aa_long_context_reasoning","value":0.716666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-coder","source":"aa-api","metric":"aa_math_index","value":39.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-coder","source":"aa-api","metric":"aa_gpqa","value":0.618,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-coder","source":"aa-api","metric":"aa_hle","value":0.045,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-coder","source":"aa-api","metric":"aa_mmlu_pro","value":0.788,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-coder","source":"aa-api","metric":"aa_livecodebench","value":0.585,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-coder","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.189393939393939,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-coder","source":"aa-api","metric":"aa_ifbench","value":0.404761904761905,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-coder","source":"aa-api","metric":"aa_long_context_reasoning","value":0.456666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-coder","source":"aa-api","metric":"aa_tau2","value":0.435672514619883,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-coder","source":"aa-api","metric":"aa_aime_2025","value":0.393333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-oss-120b","source":"aa-api","metric":"aa_math_index","value":93.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-oss-120b","source":"aa-api","metric":"aa_gpqa","value":0.782,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-oss-120b","source":"aa-api","metric":"aa_hle","value":0.196,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-oss-120b","source":"aa-api","metric":"aa_mmlu_pro","value":0.808,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-oss-120b","source":"aa-api","metric":"aa_livecodebench","value":0.878,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-oss-120b","source":"aa-api","metric":"aa_scicode","value":0.34,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-oss-120b","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.234848484848485,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-oss-120b","source":"aa-api","metric":"aa_ifbench","value":0.689795918367347,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-oss-120b","source":"aa-api","metric":"aa_long_context_reasoning","value":0.52,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-oss-120b","source":"aa-api","metric":"aa_tau2","value":0.657894736842105,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-oss-120b","source":"aa-api","metric":"aa_aime_2025","value":0.934416666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-small-2603","source":"aa-api","metric":"aa_gpqa","value":0.769,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-small-2603","source":"aa-api","metric":"aa_hle","value":0.099,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-small-2603","source":"aa-api","metric":"aa_scicode","value":0.388,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-small-2603","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.174242424242424,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-small-2603","source":"aa-api","metric":"aa_ifbench","value":0.481632653061224,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-small-2603","source":"aa-api","metric":"aa_long_context_reasoning","value":0.496666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-small-2603","source":"aa-api","metric":"aa_tau2","value":0.412280701754386,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.6v","source":"aa-api","metric":"aa_math_index","value":85.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.6v","source":"aa-api","metric":"aa_gpqa","value":0.719,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.6v","source":"aa-api","metric":"aa_hle","value":0.096,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.6v","source":"aa-api","metric":"aa_mmlu_pro","value":0.799,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.6v","source":"aa-api","metric":"aa_livecodebench","value":0.411,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.6v","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.143939393939394,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.6v","source":"aa-api","metric":"aa_ifbench","value":0.300680272108844,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.6v","source":"aa-api","metric":"aa_long_context_reasoning","value":0.486666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.6v","source":"aa-api","metric":"aa_tau2","value":0.315789473684211,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.6v","source":"aa-api","metric":"aa_aime_2025","value":0.853333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"aa-api","metric":"aa_math_index","value":84.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"aa-api","metric":"aa_gpqa","value":0.759,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"aa-api","metric":"aa_hle","value":0.126,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"aa-api","metric":"aa_mmlu_pro","value":0.824,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"aa-api","metric":"aa_livecodebench","value":0.784,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.0984848484848485,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"aa-api","metric":"aa_ifbench","value":0.606802721088435,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"aa-api","metric":"aa_long_context_reasoning","value":0.636666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"aa-api","metric":"aa_tau2","value":0.415204678362573,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"aa-api","metric":"aa_aime_2025","value":0.843333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.5-9b","source":"aa-api","metric":"aa_scicode","value":0.295,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.5-air","source":"aa-api","metric":"aa_math_index","value":80.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.5-air","source":"aa-api","metric":"aa_gpqa","value":0.733,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.5-air","source":"aa-api","metric":"aa_hle","value":0.07,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.5-air","source":"aa-api","metric":"aa_mmlu_pro","value":0.815,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.5-air","source":"aa-api","metric":"aa_livecodebench","value":0.684,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.5-air","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.204545454545455,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.5-air","source":"aa-api","metric":"aa_ifbench","value":0.375510204081633,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.5-air","source":"aa-api","metric":"aa_long_context_reasoning","value":0.466666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.5-air","source":"aa-api","metric":"aa_tau2","value":0.464912280701754,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.5-air","source":"aa-api","metric":"aa_aime_2025","value":0.806666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"ibm-granite/granite-4.2-8b","source":"aa-api","metric":"aa_gpqa","value":0.631,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"ibm-granite/granite-4.2-8b","source":"aa-api","metric":"aa_hle","value":0.097,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"ibm-granite/granite-4.2-8b","source":"aa-api","metric":"aa_scicode","value":0.315,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"ibm-granite/granite-4.2-8b","source":"aa-api","metric":"aa_long_context_reasoning","value":0.45,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o3-mini","source":"aa-api","metric":"aa_scicode","value":0.428,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o3-mini","source":"aa-api","metric":"aa_ifbench","value":0.671428571428571,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o3-mini","source":"aa-api","metric":"aa_long_context_reasoning","value":0.43,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"arcee-ai/trinity-large-thinking","source":"aa-api","metric":"aa_gpqa","value":0.752,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"arcee-ai/trinity-large-thinking","source":"aa-api","metric":"aa_hle","value":0.158,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"arcee-ai/trinity-large-thinking","source":"aa-api","metric":"aa_scicode","value":0.406,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"arcee-ai/trinity-large-thinking","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.227272727272727,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"arcee-ai/trinity-large-thinking","source":"aa-api","metric":"aa_ifbench","value":0.562585034013605,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"arcee-ai/trinity-large-thinking","source":"aa-api","metric":"aa_long_context_reasoning","value":0.38,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"arcee-ai/trinity-large-thinking","source":"aa-api","metric":"aa_tau2","value":0.900584795321637,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"inception/mercury-2","source":"aa-api","metric":"aa_gpqa","value":0.77,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"inception/mercury-2","source":"aa-api","metric":"aa_hle","value":0.171,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"inception/mercury-2","source":"aa-api","metric":"aa_scicode","value":0.377,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"inception/mercury-2","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.265151515151515,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"inception/mercury-2","source":"aa-api","metric":"aa_ifbench","value":0.697959183673469,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"inception/mercury-2","source":"aa-api","metric":"aa_long_context_reasoning","value":0.436666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"inception/mercury-2","source":"aa-api","metric":"aa_tau2","value":0.707602339181287,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4.1-mini","source":"aa-api","metric":"aa_math_index","value":46.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4.1-mini","source":"aa-api","metric":"aa_gpqa","value":0.664,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4.1-mini","source":"aa-api","metric":"aa_hle","value":0.05,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4.1-mini","source":"aa-api","metric":"aa_mmlu_pro","value":0.781,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4.1-mini","source":"aa-api","metric":"aa_livecodebench","value":0.483,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4.1-mini","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.0757575757575758,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4.1-mini","source":"aa-api","metric":"aa_ifbench","value":0.382993197278912,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4.1-mini","source":"aa-api","metric":"aa_long_context_reasoning","value":0.44,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4.1-mini","source":"aa-api","metric":"aa_tau2","value":0.529239766081871,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4.1-mini","source":"aa-api","metric":"aa_aime_2025","value":0.463333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-oss-20b","source":"aa-api","metric":"aa_math_index","value":89.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-oss-20b","source":"aa-api","metric":"aa_gpqa","value":0.688,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-oss-20b","source":"aa-api","metric":"aa_hle","value":0.11,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-oss-20b","source":"aa-api","metric":"aa_mmlu_pro","value":0.748,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-oss-20b","source":"aa-api","metric":"aa_livecodebench","value":0.777,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-oss-20b","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.106060606060606,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-oss-20b","source":"aa-api","metric":"aa_ifbench","value":0.651020408163265,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-oss-20b","source":"aa-api","metric":"aa_long_context_reasoning","value":0.346666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-oss-20b","source":"aa-api","metric":"aa_tau2","value":0.60233918128655,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-oss-20b","source":"aa-api","metric":"aa_aime_2025","value":0.893333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"aa-api","metric":"aa_math_index","value":66.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"aa-api","metric":"aa_gpqa","value":0.707,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"aa-api","metric":"aa_hle","value":0.103,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"aa-api","metric":"aa_mmlu_pro","value":0.805,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"aa-api","metric":"aa_livecodebench","value":0.707,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"aa-api","metric":"aa_scicode","value":0.33,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.0606060606060606,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"aa-api","metric":"aa_ifbench","value":0.506802721088435,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"aa-api","metric":"aa_long_context_reasoning","value":0.613333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"aa-api","metric":"aa_tau2","value":0.280701754385965,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"aa-api","metric":"aa_aime_2025","value":0.663333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"aa-api","metric":"aa_math_index","value":41,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"aa-api","metric":"aa_gpqa","value":0.655,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"aa-api","metric":"aa_hle","value":0.047,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"aa-api","metric":"aa_mmlu_pro","value":0.819,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"aa-api","metric":"aa_livecodebench","value":0.405,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"aa-api","metric":"aa_scicode","value":0.39,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.151515151515152,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"aa-api","metric":"aa_ifbench","value":0.410204081632653,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"aa-api","metric":"aa_long_context_reasoning","value":0.406666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"aa-api","metric":"aa_tau2","value":0.470760233918129,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"aa-api","metric":"aa_aime_2025","value":0.41,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-coder-30b-a3b-instruct","source":"aa-api","metric":"aa_math_index","value":29,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-coder-30b-a3b-instruct","source":"aa-api","metric":"aa_gpqa","value":0.516,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-coder-30b-a3b-instruct","source":"aa-api","metric":"aa_hle","value":0.038,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-coder-30b-a3b-instruct","source":"aa-api","metric":"aa_mmlu_pro","value":0.706,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-coder-30b-a3b-instruct","source":"aa-api","metric":"aa_livecodebench","value":0.403,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-coder-30b-a3b-instruct","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.151515151515152,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-coder-30b-a3b-instruct","source":"aa-api","metric":"aa_ifbench","value":0.326530612244898,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-coder-30b-a3b-instruct","source":"aa-api","metric":"aa_long_context_reasoning","value":0.326666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-coder-30b-a3b-instruct","source":"aa-api","metric":"aa_tau2","value":0.345029239766082,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-coder-30b-a3b-instruct","source":"aa-api","metric":"aa_aime_2025","value":0.29,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-vl-30b-a3b-instruct","source":"aa-api","metric":"aa_math_index","value":82.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-vl-30b-a3b-instruct","source":"aa-api","metric":"aa_gpqa","value":0.72,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-vl-30b-a3b-instruct","source":"aa-api","metric":"aa_hle","value":0.089,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-vl-30b-a3b-instruct","source":"aa-api","metric":"aa_mmlu_pro","value":0.807,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-vl-30b-a3b-instruct","source":"aa-api","metric":"aa_livecodebench","value":0.697,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-vl-30b-a3b-instruct","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.0606060606060606,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-vl-30b-a3b-instruct","source":"aa-api","metric":"aa_ifbench","value":0.451020408163265,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-vl-30b-a3b-instruct","source":"aa-api","metric":"aa_tau2","value":0.198830409356725,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-vl-30b-a3b-instruct","source":"aa-api","metric":"aa_aime_2025","value":0.823333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-4-maverick","source":"aa-api","metric":"aa_math_index","value":19.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-4-maverick","source":"aa-api","metric":"aa_gpqa","value":0.671,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-4-maverick","source":"aa-api","metric":"aa_hle","value":0.049,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-4-maverick","source":"aa-api","metric":"aa_mmlu_pro","value":0.809,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-4-maverick","source":"aa-api","metric":"aa_livecodebench","value":0.397,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-4-maverick","source":"aa-api","metric":"aa_scicode","value":0.317,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-4-maverick","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.0681818181818182,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-4-maverick","source":"aa-api","metric":"aa_ifbench","value":0.429931972789116,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-4-maverick","source":"aa-api","metric":"aa_long_context_reasoning","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-4-maverick","source":"aa-api","metric":"aa_tau2","value":0.178362573099415,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-4-maverick","source":"aa-api","metric":"aa_aime_2025","value":0.193333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-coder-next","source":"aa-api","metric":"aa_gpqa","value":0.737,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-coder-next","source":"aa-api","metric":"aa_hle","value":0.101,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-coder-next","source":"aa-api","metric":"aa_scicode","value":0.362,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-coder-next","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.181818181818182,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-coder-next","source":"aa-api","metric":"aa_ifbench","value":0.352380952380952,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-coder-next","source":"aa-api","metric":"aa_long_context_reasoning","value":0.47,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-coder-next","source":"aa-api","metric":"aa_tau2","value":0.795321637426901,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-medium-3.1","source":"aa-api","metric":"aa_math_index","value":38.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-medium-3.1","source":"aa-api","metric":"aa_gpqa","value":0.588,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-medium-3.1","source":"aa-api","metric":"aa_hle","value":0.047,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-medium-3.1","source":"aa-api","metric":"aa_mmlu_pro","value":0.683,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-medium-3.1","source":"aa-api","metric":"aa_livecodebench","value":0.406,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-medium-3.1","source":"aa-api","metric":"aa_scicode","value":0.324,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-medium-3.1","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.106060606060606,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-medium-3.1","source":"aa-api","metric":"aa_ifbench","value":0.397959183673469,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-medium-3.1","source":"aa-api","metric":"aa_long_context_reasoning","value":0.426666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-medium-3.1","source":"aa-api","metric":"aa_tau2","value":0.406432748538012,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-medium-3.1","source":"aa-api","metric":"aa_aime_2025","value":0.383333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-premier-v1","source":"aa-api","metric":"aa_math_index","value":17.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-premier-v1","source":"aa-api","metric":"aa_gpqa","value":0.569,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-premier-v1","source":"aa-api","metric":"aa_hle","value":0.042,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-premier-v1","source":"aa-api","metric":"aa_mmlu_pro","value":0.733,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-premier-v1","source":"aa-api","metric":"aa_livecodebench","value":0.317,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-premier-v1","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.0681818181818182,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-premier-v1","source":"aa-api","metric":"aa_ifbench","value":0.361904761904762,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-premier-v1","source":"aa-api","metric":"aa_long_context_reasoning","value":0.343333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-premier-v1","source":"aa-api","metric":"aa_tau2","value":0.383040935672515,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-premier-v1","source":"aa-api","metric":"aa_aime_2025","value":0.173333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-medium-3","source":"aa-api","metric":"aa_math_index","value":30.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-medium-3","source":"aa-api","metric":"aa_gpqa","value":0.578,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-medium-3","source":"aa-api","metric":"aa_hle","value":0.041,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-medium-3","source":"aa-api","metric":"aa_mmlu_pro","value":0.76,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-medium-3","source":"aa-api","metric":"aa_livecodebench","value":0.4,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-medium-3","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.0378787878787879,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-medium-3","source":"aa-api","metric":"aa_ifbench","value":0.392517006802721,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-medium-3","source":"aa-api","metric":"aa_long_context_reasoning","value":0.313333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-medium-3","source":"aa-api","metric":"aa_tau2","value":0.242690058479532,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-medium-3","source":"aa-api","metric":"aa_aime_2025","value":0.303333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-oss-20b","source":"aa-api","metric":"aa_scicode","value":0.389,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3-nano-30b-a3b","source":"aa-api","metric":"aa_math_index","value":91,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3-nano-30b-a3b","source":"aa-api","metric":"aa_gpqa","value":0.757,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3-nano-30b-a3b","source":"aa-api","metric":"aa_hle","value":0.114,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3-nano-30b-a3b","source":"aa-api","metric":"aa_mmlu_pro","value":0.794,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3-nano-30b-a3b","source":"aa-api","metric":"aa_livecodebench","value":0.741,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3-nano-30b-a3b","source":"aa-api","metric":"aa_scicode","value":0.306,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3-nano-30b-a3b","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.136363636363636,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3-nano-30b-a3b","source":"aa-api","metric":"aa_ifbench","value":0.710884353741497,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3-nano-30b-a3b","source":"aa-api","metric":"aa_long_context_reasoning","value":0.38,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3-nano-30b-a3b","source":"aa-api","metric":"aa_tau2","value":0.409356725146199,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3-nano-30b-a3b","source":"aa-api","metric":"aa_aime_2025","value":0.91,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-2.5-flash-lite","source":"aa-api","metric":"aa_math_index","value":53.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-2.5-flash-lite","source":"aa-api","metric":"aa_gpqa","value":0.625,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-2.5-flash-lite","source":"aa-api","metric":"aa_hle","value":0.068,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-2.5-flash-lite","source":"aa-api","metric":"aa_mmlu_pro","value":0.759,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-2.5-flash-lite","source":"aa-api","metric":"aa_livecodebench","value":0.593,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-2.5-flash-lite","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.0454545454545455,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-2.5-flash-lite","source":"aa-api","metric":"aa_ifbench","value":0.498639455782313,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-2.5-flash-lite","source":"aa-api","metric":"aa_long_context_reasoning","value":0.556666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-2.5-flash-lite","source":"aa-api","metric":"aa_tau2","value":0.190058479532164,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-2.5-flash-lite","source":"aa-api","metric":"aa_aime_2025","value":0.533333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4o","source":"aa-api","metric":"aa_math_index","value":6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4o","source":"aa-api","metric":"aa_gpqa","value":0.543,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4o","source":"aa-api","metric":"aa_hle","value":0.024,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4o","source":"aa-api","metric":"aa_mmlu_pro","value":0.748,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4o","source":"aa-api","metric":"aa_livecodebench","value":0.309,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4o","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.0833333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4o","source":"aa-api","metric":"aa_ifbench","value":0.342857142857143,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4o","source":"aa-api","metric":"aa_long_context_reasoning","value":0.493333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4o","source":"aa-api","metric":"aa_tau2","value":0.251461988304094,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4o","source":"aa-api","metric":"aa_aime_2025","value":0.06,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-vl-8b-instruct","source":"aa-api","metric":"aa_math_index","value":30.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-vl-8b-instruct","source":"aa-api","metric":"aa_gpqa","value":0.579,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-vl-8b-instruct","source":"aa-api","metric":"aa_hle","value":0.038,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-vl-8b-instruct","source":"aa-api","metric":"aa_mmlu_pro","value":0.749,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-vl-8b-instruct","source":"aa-api","metric":"aa_livecodebench","value":0.353,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-vl-8b-instruct","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.0378787878787879,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-vl-8b-instruct","source":"aa-api","metric":"aa_ifbench","value":0.398639455782313,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-vl-8b-instruct","source":"aa-api","metric":"aa_long_context_reasoning","value":0.333333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-vl-8b-instruct","source":"aa-api","metric":"aa_tau2","value":0.292397660818713,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-vl-8b-instruct","source":"aa-api","metric":"aa_aime_2025","value":0.306666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4.1-nano","source":"aa-api","metric":"aa_math_index","value":24,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4.1-nano","source":"aa-api","metric":"aa_gpqa","value":0.512,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4.1-nano","source":"aa-api","metric":"aa_hle","value":0.038,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4.1-nano","source":"aa-api","metric":"aa_mmlu_pro","value":0.657,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4.1-nano","source":"aa-api","metric":"aa_livecodebench","value":0.326,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4.1-nano","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.0378787878787879,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4.1-nano","source":"aa-api","metric":"aa_ifbench","value":0.320408163265306,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4.1-nano","source":"aa-api","metric":"aa_long_context_reasoning","value":0.203333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4.1-nano","source":"aa-api","metric":"aa_tau2","value":0.172514619883041,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4.1-nano","source":"aa-api","metric":"aa_aime_2025","value":0.24,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"upstage/solar-pro-3","source":"aa-api","metric":"aa_gpqa","value":0.724,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"upstage/solar-pro-3","source":"aa-api","metric":"aa_hle","value":0.103,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"upstage/solar-pro-3","source":"aa-api","metric":"aa_scicode","value":0.255,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"upstage/solar-pro-3","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.0757575757575758,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"upstage/solar-pro-3","source":"aa-api","metric":"aa_ifbench","value":0.712018140589569,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"upstage/solar-pro-3","source":"aa-api","metric":"aa_long_context_reasoning","value":0.323333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"upstage/solar-pro-3","source":"aa-api","metric":"aa_tau2","value":0.862573099415205,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4o-2024-08-06","source":"aa-api","metric":"aa_gpqa","value":0.521,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4o-2024-08-06","source":"aa-api","metric":"aa_hle","value":0.023,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4o-2024-08-06","source":"aa-api","metric":"aa_livecodebench","value":0.317,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4o-2024-08-06","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.0833333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4o-2024-08-06","source":"aa-api","metric":"aa_ifbench","value":0.359863945578231,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4o-2024-08-06","source":"aa-api","metric":"aa_long_context_reasoning","value":0.41,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4o-2024-08-06","source":"aa-api","metric":"aa_tau2","value":0.289473684210526,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"aa-api","metric":"aa_math_index","value":14,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"aa-api","metric":"aa_gpqa","value":0.491,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"aa-api","metric":"aa_hle","value":0.036,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"aa-api","metric":"aa_mmlu_pro","value":0.72,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"aa-api","metric":"aa_livecodebench","value":0.276,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.0454545454545455,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"aa-api","metric":"aa_ifbench","value":0.368707482993197,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"aa-api","metric":"aa_tau2","value":0.345029239766082,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"aa-api","metric":"aa_aime_2025","value":0.14,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"perplexity/sonar","source":"aa-api","metric":"aa_gpqa","value":0.471,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"perplexity/sonar","source":"aa-api","metric":"aa_hle","value":0.049,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"perplexity/sonar","source":"aa-api","metric":"aa_mmlu_pro","value":0.689,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"perplexity/sonar","source":"aa-api","metric":"aa_livecodebench","value":0.295,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"aa-api","metric":"aa_math_index","value":7.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"aa-api","metric":"aa_gpqa","value":0.498,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"aa-api","metric":"aa_hle","value":0.036,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"aa-api","metric":"aa_mmlu_pro","value":0.713,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"aa-api","metric":"aa_livecodebench","value":0.288,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.0303030303030303,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"aa-api","metric":"aa_ifbench","value":0.470748299319728,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"aa-api","metric":"aa_long_context_reasoning","value":0.156666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"aa-api","metric":"aa_tau2","value":0.266081871345029,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"aa-api","metric":"aa_aime_2025","value":0.0766666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-30b-a3b","source":"aa-api","metric":"aa_math_index","value":72.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-30b-a3b","source":"aa-api","metric":"aa_gpqa","value":0.616,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-30b-a3b","source":"aa-api","metric":"aa_hle","value":0.062,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-30b-a3b","source":"aa-api","metric":"aa_mmlu_pro","value":0.777,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-30b-a3b","source":"aa-api","metric":"aa_livecodebench","value":0.506,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-30b-a3b","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.0681818181818182,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-30b-a3b","source":"aa-api","metric":"aa_ifbench","value":0.414965986394558,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-30b-a3b","source":"aa-api","metric":"aa_long_context_reasoning","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-30b-a3b","source":"aa-api","metric":"aa_tau2","value":0.260233918128655,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-30b-a3b","source":"aa-api","metric":"aa_aime_2025","value":0.723333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"perplexity/sonar-pro","source":"aa-api","metric":"aa_gpqa","value":0.578,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"perplexity/sonar-pro","source":"aa-api","metric":"aa_hle","value":0.066,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"perplexity/sonar-pro","source":"aa-api","metric":"aa_mmlu_pro","value":0.755,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"perplexity/sonar-pro","source":"aa-api","metric":"aa_livecodebench","value":0.275,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.5v","source":"aa-api","metric":"aa_math_index","value":73,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.5v","source":"aa-api","metric":"aa_gpqa","value":0.684,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.5v","source":"aa-api","metric":"aa_hle","value":0.063,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.5v","source":"aa-api","metric":"aa_mmlu_pro","value":0.788,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.5v","source":"aa-api","metric":"aa_livecodebench","value":0.604,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.5v","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.0681818181818182,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.5v","source":"aa-api","metric":"aa_ifbench","value":0.342176870748299,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.5v","source":"aa-api","metric":"aa_long_context_reasoning","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.5v","source":"aa-api","metric":"aa_tau2","value":0.225146198830409,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-4.5v","source":"aa-api","metric":"aa_aime_2025","value":0.73,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-32b","source":"aa-api","metric":"aa_math_index","value":73,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-32b","source":"aa-api","metric":"aa_gpqa","value":0.668,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-32b","source":"aa-api","metric":"aa_hle","value":0.074,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-32b","source":"aa-api","metric":"aa_mmlu_pro","value":0.798,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-32b","source":"aa-api","metric":"aa_livecodebench","value":0.546,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-32b","source":"aa-api","metric":"aa_ifbench","value":0.363265306122449,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-32b","source":"aa-api","metric":"aa_long_context_reasoning","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-32b","source":"aa-api","metric":"aa_aime_2025","value":0.73,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4o-2024-05-13","source":"aa-api","metric":"aa_gpqa","value":0.526,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4o-2024-05-13","source":"aa-api","metric":"aa_hle","value":0.018,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4o-2024-05-13","source":"aa-api","metric":"aa_mmlu_pro","value":0.74,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4o-2024-05-13","source":"aa-api","metric":"aa_livecodebench","value":0.334,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-32b","source":"aa-api","metric":"aa_scicode","value":0.36,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-32b","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.0303030303030303,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-32b","source":"aa-api","metric":"aa_tau2","value":0.298245614035088,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4-turbo","source":"aa-api","metric":"aa_hle","value":0.031,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4-turbo","source":"aa-api","metric":"aa_mmlu_pro","value":0.694,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4-turbo","source":"aa-api","metric":"aa_livecodebench","value":0.291,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-pro-v1","source":"aa-api","metric":"aa_math_index","value":7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-pro-v1","source":"aa-api","metric":"aa_gpqa","value":0.499,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-pro-v1","source":"aa-api","metric":"aa_hle","value":0.032,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-pro-v1","source":"aa-api","metric":"aa_mmlu_pro","value":0.691,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-pro-v1","source":"aa-api","metric":"aa_livecodebench","value":0.233,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-pro-v1","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.0606060606060606,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-pro-v1","source":"aa-api","metric":"aa_ifbench","value":0.380952380952381,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-pro-v1","source":"aa-api","metric":"aa_long_context_reasoning","value":0.21,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-pro-v1","source":"aa-api","metric":"aa_tau2","value":0.140350877192982,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-pro-v1","source":"aa-api","metric":"aa_aime_2025","value":0.07,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"cohere/command-a","source":"aa-api","metric":"aa_math_index","value":13,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"cohere/command-a","source":"aa-api","metric":"aa_mmlu_pro","value":0.712,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"cohere/command-a","source":"aa-api","metric":"aa_livecodebench","value":0.287,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"cohere/command-a","source":"aa-api","metric":"aa_aime_2025","value":0.13,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"aa-api","metric":"aa_math_index","value":4.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"aa-api","metric":"aa_gpqa","value":0.259,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"aa-api","metric":"aa_hle","value":0.053,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"aa-api","metric":"aa_mmlu_pro","value":0.476,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"aa-api","metric":"aa_livecodebench","value":0.116,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.00757575757575758,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"aa-api","metric":"aa_ifbench","value":0.285714285714286,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"aa-api","metric":"aa_long_context_reasoning","value":0.18,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"aa-api","metric":"aa_tau2","value":0.16374269005848,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"aa-api","metric":"aa_aime_2025","value":0.0433333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-large-2407","source":"aa-api","metric":"aa_math_index","value":0,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-large-2407","source":"aa-api","metric":"aa_gpqa","value":0.472,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-large-2407","source":"aa-api","metric":"aa_hle","value":0.029,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-large-2407","source":"aa-api","metric":"aa_mmlu_pro","value":0.683,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-large-2407","source":"aa-api","metric":"aa_livecodebench","value":0.267,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-large-2407","source":"aa-api","metric":"aa_ifbench","value":0.316326530612245,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-large-2407","source":"aa-api","metric":"aa_long_context_reasoning","value":0.02,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-large-2407","source":"aa-api","metric":"aa_tau2","value":0.330409356725146,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-large-2407","source":"aa-api","metric":"aa_aime_2025","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"aa-api","metric":"aa_gpqa","value":0.417,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"aa-api","metric":"aa_hle","value":0.035,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"aa-api","metric":"aa_mmlu_pro","value":0.635,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"aa-api","metric":"aa_livecodebench","value":0.295,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-14b","source":"aa-api","metric":"aa_math_index","value":58,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-14b","source":"aa-api","metric":"aa_gpqa","value":0.604,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-14b","source":"aa-api","metric":"aa_hle","value":0.045,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-14b","source":"aa-api","metric":"aa_mmlu_pro","value":0.774,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-14b","source":"aa-api","metric":"aa_livecodebench","value":0.523,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-14b","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.053030303030303,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-14b","source":"aa-api","metric":"aa_ifbench","value":0.405442176870748,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-14b","source":"aa-api","metric":"aa_long_context_reasoning","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-14b","source":"aa-api","metric":"aa_tau2","value":0.345029239766082,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-14b","source":"aa-api","metric":"aa_aime_2025","value":0.58,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4","source":"aa-api","metric":"aa_gpqa","value":0.349,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4","source":"aa-api","metric":"aa_mmlu_pro","value":0.562,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4","source":"aa-api","metric":"aa_ifbench","value":0.331972789115646,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"aa-api","metric":"aa_math_index","value":4.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"aa-api","metric":"aa_gpqa","value":0.462,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"aa-api","metric":"aa_hle","value":0.038,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"aa-api","metric":"aa_mmlu_pro","value":0.652,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"aa-api","metric":"aa_livecodebench","value":0.252,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"aa-api","metric":"aa_ifbench","value":0.263945578231293,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"aa-api","metric":"aa_long_context_reasoning","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"aa-api","metric":"aa_tau2","value":0.195906432748538,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"aa-api","metric":"aa_aime_2025","value":0.0433333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-lite-v1","source":"aa-api","metric":"aa_math_index","value":7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-lite-v1","source":"aa-api","metric":"aa_gpqa","value":0.433,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-lite-v1","source":"aa-api","metric":"aa_hle","value":0.043,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-lite-v1","source":"aa-api","metric":"aa_mmlu_pro","value":0.59,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-lite-v1","source":"aa-api","metric":"aa_livecodebench","value":0.167,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-lite-v1","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.00757575757575758,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-lite-v1","source":"aa-api","metric":"aa_ifbench","value":0.341496598639456,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-lite-v1","source":"aa-api","metric":"aa_long_context_reasoning","value":0.19,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-lite-v1","source":"aa-api","metric":"aa_tau2","value":0.175438596491228,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-lite-v1","source":"aa-api","metric":"aa_aime_2025","value":0.07,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4o-mini","source":"aa-api","metric":"aa_math_index","value":14.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4o-mini","source":"aa-api","metric":"aa_gpqa","value":0.426,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4o-mini","source":"aa-api","metric":"aa_hle","value":0.042,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4o-mini","source":"aa-api","metric":"aa_mmlu_pro","value":0.648,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4o-mini","source":"aa-api","metric":"aa_livecodebench","value":0.234,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4o-mini","source":"aa-api","metric":"aa_ifbench","value":0.30952380952381,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-4o-mini","source":"aa-api","metric":"aa_aime_2025","value":0.146666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"aa-api","metric":"aa_math_index","value":4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"aa-api","metric":"aa_gpqa","value":0.409,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"aa-api","metric":"aa_hle","value":0.045,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"aa-api","metric":"aa_mmlu_pro","value":0.676,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"aa-api","metric":"aa_livecodebench","value":0.232,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.0303030303030303,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"aa-api","metric":"aa_ifbench","value":0.34421768707483,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"aa-api","metric":"aa_tau2","value":0.152046783625731,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"aa-api","metric":"aa_aime_2025","value":0.04,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-saba","source":"aa-api","metric":"aa_gpqa","value":0.424,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-saba","source":"aa-api","metric":"aa_hle","value":0.043,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-saba","source":"aa-api","metric":"aa_mmlu_pro","value":0.611,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-4-scout","source":"aa-api","metric":"aa_math_index","value":14,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-4-scout","source":"aa-api","metric":"aa_gpqa","value":0.587,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-4-scout","source":"aa-api","metric":"aa_hle","value":0.038,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-4-scout","source":"aa-api","metric":"aa_mmlu_pro","value":0.752,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-4-scout","source":"aa-api","metric":"aa_livecodebench","value":0.299,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-4-scout","source":"aa-api","metric":"aa_scicode","value":0.213,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-4-scout","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.0151515151515152,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-4-scout","source":"aa-api","metric":"aa_ifbench","value":0.395238095238095,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-4-scout","source":"aa-api","metric":"aa_long_context_reasoning","value":0.277,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-4-scout","source":"aa-api","metric":"aa_tau2","value":0.154970760233918,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-4-scout","source":"aa-api","metric":"aa_aime_2025","value":0.14,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-14b","source":"aa-api","metric":"aa_scicode","value":0.307,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nousresearch/hermes-3-llama-3.1-70b","source":"aa-api","metric":"aa_gpqa","value":0.401,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nousresearch/hermes-3-llama-3.1-70b","source":"aa-api","metric":"aa_hle","value":0.04,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nousresearch/hermes-3-llama-3.1-70b","source":"aa-api","metric":"aa_mmlu_pro","value":0.571,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nousresearch/hermes-3-llama-3.1-70b","source":"aa-api","metric":"aa_livecodebench","value":0.188,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"microsoft/phi-4","source":"aa-api","metric":"aa_math_index","value":18,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"microsoft/phi-4","source":"aa-api","metric":"aa_gpqa","value":0.575,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"microsoft/phi-4","source":"aa-api","metric":"aa_hle","value":0.038,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"microsoft/phi-4","source":"aa-api","metric":"aa_mmlu_pro","value":0.714,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"microsoft/phi-4","source":"aa-api","metric":"aa_livecodebench","value":0.231,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"microsoft/phi-4","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.0378787878787879,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"microsoft/phi-4","source":"aa-api","metric":"aa_ifbench","value":0.235374149659864,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"microsoft/phi-4","source":"aa-api","metric":"aa_long_context_reasoning","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"microsoft/phi-4","source":"aa-api","metric":"aa_tau2","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"microsoft/phi-4","source":"aa-api","metric":"aa_aime_2025","value":0.18,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-micro-v1","source":"aa-api","metric":"aa_math_index","value":6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-micro-v1","source":"aa-api","metric":"aa_gpqa","value":0.358,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-micro-v1","source":"aa-api","metric":"aa_hle","value":0.046,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-micro-v1","source":"aa-api","metric":"aa_mmlu_pro","value":0.531,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-micro-v1","source":"aa-api","metric":"aa_livecodebench","value":0.14,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-micro-v1","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.0151515151515152,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-micro-v1","source":"aa-api","metric":"aa_ifbench","value":0.293877551020408,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-micro-v1","source":"aa-api","metric":"aa_long_context_reasoning","value":0.13,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-micro-v1","source":"aa-api","metric":"aa_tau2","value":0.140350877192982,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-micro-v1","source":"aa-api","metric":"aa_aime_2025","value":0.06,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-large","source":"aa-api","metric":"aa_gpqa","value":0.351,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-large","source":"aa-api","metric":"aa_hle","value":0.035,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-large","source":"aa-api","metric":"aa_mmlu_pro","value":0.515,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-large","source":"aa-api","metric":"aa_livecodebench","value":0.178,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mixtral-8x22b-instruct","source":"aa-api","metric":"aa_gpqa","value":0.332,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mixtral-8x22b-instruct","source":"aa-api","metric":"aa_hle","value":0.04,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mixtral-8x22b-instruct","source":"aa-api","metric":"aa_mmlu_pro","value":0.537,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mixtral-8x22b-instruct","source":"aa-api","metric":"aa_livecodebench","value":0.148,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"aa-api","metric":"aa_math_index","value":3.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"aa-api","metric":"aa_gpqa","value":0.255,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"aa-api","metric":"aa_hle","value":0.053,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"aa-api","metric":"aa_mmlu_pro","value":0.347,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"aa-api","metric":"aa_livecodebench","value":0.083,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"aa-api","metric":"aa_ifbench","value":0.261904761904762,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"aa-api","metric":"aa_long_context_reasoning","value":0.0433333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"aa-api","metric":"aa_tau2","value":0.210526315789474,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"aa-api","metric":"aa_aime_2025","value":0.0333333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"rekaai/reka-flash-3","source":"aa-api","metric":"aa_math_index","value":33.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"rekaai/reka-flash-3","source":"aa-api","metric":"aa_gpqa","value":0.529,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"rekaai/reka-flash-3","source":"aa-api","metric":"aa_hle","value":0.044,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"rekaai/reka-flash-3","source":"aa-api","metric":"aa_mmlu_pro","value":0.669,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"rekaai/reka-flash-3","source":"aa-api","metric":"aa_livecodebench","value":0.435,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"rekaai/reka-flash-3","source":"aa-api","metric":"aa_terminal_bench_hard","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"rekaai/reka-flash-3","source":"aa-api","metric":"aa_ifbench","value":0.304081632653061,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"rekaai/reka-flash-3","source":"aa-api","metric":"aa_long_context_reasoning","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"rekaai/reka-flash-3","source":"aa-api","metric":"aa_tau2","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"rekaai/reka-flash-3","source":"aa-api","metric":"aa_aime_2025","value":0.336666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-3.5-turbo","source":"aa-api","metric":"aa_gpqa","value":0.297,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-3.5-turbo","source":"aa-api","metric":"aa_mmlu_pro","value":0.462,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"ibm-granite/granite-4.0-h-micro","source":"aa-api","metric":"aa_math_index","value":6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"ibm-granite/granite-4.0-h-micro","source":"aa-api","metric":"aa_gpqa","value":0.336,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"ibm-granite/granite-4.0-h-micro","source":"aa-api","metric":"aa_hle","value":0.05,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"ibm-granite/granite-4.0-h-micro","source":"aa-api","metric":"aa_mmlu_pro","value":0.447,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"ibm-granite/granite-4.0-h-micro","source":"aa-api","metric":"aa_livecodebench","value":0.18,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"ibm-granite/granite-4.0-h-micro","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.0151515151515152,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"ibm-granite/granite-4.0-h-micro","source":"aa-api","metric":"aa_ifbench","value":0.247619047619048,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"ibm-granite/granite-4.0-h-micro","source":"aa-api","metric":"aa_long_context_reasoning","value":0.07,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"ibm-granite/granite-4.0-h-micro","source":"aa-api","metric":"aa_tau2","value":0.125730994152047,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"ibm-granite/granite-4.0-h-micro","source":"aa-api","metric":"aa_aime_2025","value":0.06,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-3-27b-it","source":"aa-api","metric":"aa_math_index","value":20.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-3-27b-it","source":"aa-api","metric":"aa_gpqa","value":0.428,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-3-27b-it","source":"aa-api","metric":"aa_hle","value":0.044,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-3-27b-it","source":"aa-api","metric":"aa_mmlu_pro","value":0.669,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-3-27b-it","source":"aa-api","metric":"aa_livecodebench","value":0.137,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-3-27b-it","source":"aa-api","metric":"aa_scicode","value":0.233,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-3-27b-it","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.0378787878787879,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-3-27b-it","source":"aa-api","metric":"aa_ifbench","value":0.318367346938776,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-3-27b-it","source":"aa-api","metric":"aa_long_context_reasoning","value":0.0733333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-3-27b-it","source":"aa-api","metric":"aa_tau2","value":0.105263157894737,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-3-27b-it","source":"aa-api","metric":"aa_aime_2025","value":0.206666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-3-4b-it","source":"aa-api","metric":"aa_math_index","value":12.7,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-3-4b-it","source":"aa-api","metric":"aa_gpqa","value":0.291,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-3-4b-it","source":"aa-api","metric":"aa_hle","value":0.053,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-3-4b-it","source":"aa-api","metric":"aa_mmlu_pro","value":0.417,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-3-4b-it","source":"aa-api","metric":"aa_livecodebench","value":0.112,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-3-4b-it","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.00757575757575758,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-3-4b-it","source":"aa-api","metric":"aa_ifbench","value":0.282993197278912,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-3-4b-it","source":"aa-api","metric":"aa_long_context_reasoning","value":0.0666666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-3-4b-it","source":"aa-api","metric":"aa_tau2","value":0.0497076023391813,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-3-4b-it","source":"aa-api","metric":"aa_aime_2025","value":0.126666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"aa-api","metric":"aa_math_index","value":0,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"aa-api","metric":"aa_gpqa","value":0.196,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"aa-api","metric":"aa_hle","value":0.055,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"aa-api","metric":"aa_mmlu_pro","value":0.2,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"aa-api","metric":"aa_livecodebench","value":0.019,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"aa-api","metric":"aa_terminal_bench_hard","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"aa-api","metric":"aa_ifbench","value":0.227891156462585,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"aa-api","metric":"aa_long_context_reasoning","value":0.0666666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"aa-api","metric":"aa_tau2","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"aa-api","metric":"aa_aime_2025","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-3-12b-it","source":"aa-api","metric":"aa_math_index","value":18.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-3-12b-it","source":"aa-api","metric":"aa_gpqa","value":0.349,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-3-12b-it","source":"aa-api","metric":"aa_hle","value":0.042,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-3-12b-it","source":"aa-api","metric":"aa_mmlu_pro","value":0.595,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-3-12b-it","source":"aa-api","metric":"aa_livecodebench","value":0.137,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-3-12b-it","source":"aa-api","metric":"aa_scicode","value":0.164,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-3-12b-it","source":"aa-api","metric":"aa_terminal_bench_hard","value":0.00757575757575758,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-3-12b-it","source":"aa-api","metric":"aa_ifbench","value":0.36734693877551,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-3-12b-it","source":"aa-api","metric":"aa_long_context_reasoning","value":0.0833333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-3-12b-it","source":"aa-api","metric":"aa_tau2","value":0.108187134502924,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemma-3-12b-it","source":"aa-api","metric":"aa_aime_2025","value":0.183333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"anthropic/claude-opus-5.5","source":"aa-api","metric":"aa_output_tokens_per_second","value":95.965,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Max"},{"modelId":"anthropic/claude-opus-5.5","source":"aa-api","metric":"aa_time_to_first_token_s","value":661.584,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Max"},{"modelId":"anthropic/claude-sonnet-5.5","source":"aa-api","metric":"aa_output_tokens_per_second","value":137.142,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Max"},{"modelId":"anthropic/claude-sonnet-5.5","source":"aa-api","metric":"aa_time_to_first_token_s","value":372.255,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Max"},{"modelId":"anthropic/claude-fable-5.1","source":"aa-api","metric":"aa_output_tokens_per_second","value":73.141,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Max"},{"modelId":"anthropic/claude-fable-5.1","source":"aa-api","metric":"aa_time_to_first_token_s","value":200.63,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Max"},{"modelId":"openai/gpt-6-astra","source":"aa-api","metric":"aa_output_tokens_per_second","value":68.466,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Max"},{"modelId":"openai/gpt-6-astra","source":"aa-api","metric":"aa_time_to_first_token_s","value":238.869,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Max"},{"modelId":"google/gemini-4-argon","source":"aa-api","metric":"aa_output_tokens_per_second","value":81.009,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"High"},{"modelId":"google/gemini-4-argon","source":"aa-api","metric":"aa_time_to_first_token_s","value":28.473,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"High"},{"modelId":"meta/muse-wonder","source":"aa-api","metric":"aa_output_tokens_per_second","value":148.227,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Max"},{"modelId":"meta/muse-wonder","source":"aa-api","metric":"aa_time_to_first_token_s","value":34.574,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Max"},{"modelId":"openai/gpt-6.1-sol","source":"aa-api","metric":"aa_output_tokens_per_second","value":52.211,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Max"},{"modelId":"openai/gpt-6.1-sol","source":"aa-api","metric":"aa_time_to_first_token_s","value":264.289,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Max"},{"modelId":"meta/muse-spark-1.3","source":"aa-api","metric":"aa_output_tokens_per_second","value":119.305,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Max"},{"modelId":"meta/muse-spark-1.3","source":"aa-api","metric":"aa_time_to_first_token_s","value":38.237,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Max"},{"modelId":"x-ai/grok-4.7","source":"aa-api","metric":"aa_output_tokens_per_second","value":74.295,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Xhigh"},{"modelId":"x-ai/grok-4.7","source":"aa-api","metric":"aa_time_to_first_token_s","value":21.703,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Xhigh"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"aa-api","metric":"aa_output_tokens_per_second","value":40.857,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"aa-api","metric":"aa_time_to_first_token_s","value":2.985,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.8-max-0902","source":"aa-api","metric":"aa_output_tokens_per_second","value":37.16,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"0902"},{"modelId":"qwen/qwen3.8-max-0902","source":"aa-api","metric":"aa_time_to_first_token_s","value":1.84,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"0902"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"aa-api","metric":"aa_output_tokens_per_second","value":211.604,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Max"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"aa-api","metric":"aa_time_to_first_token_s","value":1.034,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Max"},{"modelId":"z-ai/glm-5.3","source":"aa-api","metric":"aa_output_tokens_per_second","value":76.005,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Max"},{"modelId":"z-ai/glm-5.3","source":"aa-api","metric":"aa_time_to_first_token_s","value":2.84,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Max"},{"modelId":"stepfun/step-5-preview","source":"aa-api","metric":"aa_output_tokens_per_second","value":85.694,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"stepfun/step-5-preview","source":"aa-api","metric":"aa_time_to_first_token_s","value":1.379,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k3","source":"aa-api","metric":"aa_output_tokens_per_second","value":40.979,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Max"},{"modelId":"moonshotai/kimi-k3","source":"aa-api","metric":"aa_time_to_first_token_s","value":3.103,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Max"},{"modelId":"anthropic/claude-haiku-5.5","source":"aa-api","metric":"aa_output_tokens_per_second","value":238.822,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Max"},{"modelId":"anthropic/claude-haiku-5.5","source":"aa-api","metric":"aa_time_to_first_token_s","value":291.1,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Max"},{"modelId":"openai/gpt-5.6-terra","source":"aa-api","metric":"aa_output_tokens_per_second","value":141.523,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Max"},{"modelId":"openai/gpt-5.6-terra","source":"aa-api","metric":"aa_time_to_first_token_s","value":207.159,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Max"},{"modelId":"z-ai/glm-5.3-flash","source":"aa-api","metric":"aa_output_tokens_per_second","value":75.514,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"z-ai/glm-5.3-flash","source":"aa-api","metric":"aa_time_to_first_token_s","value":2.081,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"inclusionai/ling-3.1-flash","source":"aa-api","metric":"aa_output_tokens_per_second","value":215.661,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"inclusionai/ling-3.1-flash","source":"aa-api","metric":"aa_time_to_first_token_s","value":1.156,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.8-flash","source":"aa-api","metric":"aa_output_tokens_per_second","value":140.805,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"High"},{"modelId":"google/gemini-3.8-flash","source":"aa-api","metric":"aa_time_to_first_token_s","value":15.532,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"High"},{"modelId":"qwen/qwen3.8-2.4t-a95b","source":"aa-api","metric":"aa_output_tokens_per_second","value":36.826,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.8-2.4t-a95b","source":"aa-api","metric":"aa_time_to_first_token_s","value":1.971,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"aa-api","metric":"aa_output_tokens_per_second","value":233.319,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Max"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"aa-api","metric":"aa_time_to_first_token_s","value":0.704,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Max"},{"modelId":"meta/muse-spark-open","source":"aa-api","metric":"aa_output_tokens_per_second","value":139.866,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Xhigh"},{"modelId":"meta/muse-spark-open","source":"aa-api","metric":"aa_time_to_first_token_s","value":0.466,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Xhigh"},{"modelId":"mistralai/mistral-large-4-0","source":"aa-api","metric":"aa_output_tokens_per_second","value":62.252,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-large-4-0","source":"aa-api","metric":"aa_time_to_first_token_s","value":0.72,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-6-luna","source":"aa-api","metric":"aa_output_tokens_per_second","value":127.229,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Max"},{"modelId":"openai/gpt-6-luna","source":"aa-api","metric":"aa_time_to_first_token_s","value":106.434,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Max"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"aa-api","metric":"aa_output_tokens_per_second","value":46.153,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"aa-api","metric":"aa_time_to_first_token_s","value":4.26,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"aa-api","metric":"aa_output_tokens_per_second","value":95.868,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Max"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"aa-api","metric":"aa_time_to_first_token_s","value":1.051,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Max"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"aa-api","metric":"aa_output_tokens_per_second","value":195.857,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Max"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"aa-api","metric":"aa_time_to_first_token_s","value":1.098,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Max"},{"modelId":"z-ai/glm-5.2","source":"aa-api","metric":"aa_output_tokens_per_second","value":135.139,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Non-reasoning"},{"modelId":"z-ai/glm-5.2","source":"aa-api","metric":"aa_time_to_first_token_s","value":0.698,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Non-reasoning"},{"modelId":"qwen/qwen3.8-27b","source":"aa-api","metric":"aa_output_tokens_per_second","value":39.148,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Xhigh"},{"modelId":"qwen/qwen3.8-27b","source":"aa-api","metric":"aa_time_to_first_token_s","value":1.303,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Xhigh"},{"modelId":"openai/gpt-5.3-codex","source":"aa-api","metric":"aa_output_tokens_per_second","value":121.625,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Xhigh"},{"modelId":"openai/gpt-5.3-codex","source":"aa-api","metric":"aa_time_to_first_token_s","value":45.465,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Xhigh"},{"modelId":"google/gemini-3.1-pro-preview","source":"aa-api","metric":"aa_output_tokens_per_second","value":129.224,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.1-pro-preview","source":"aa-api","metric":"aa_time_to_first_token_s","value":14.445,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m3","source":"aa-api","metric":"aa_output_tokens_per_second","value":104.541,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"minimax/minimax-m3","source":"aa-api","metric":"aa_time_to_first_token_s","value":0.716,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"upstage/solar-pro4","source":"aa-api","metric":"aa_output_tokens_per_second","value":117.35,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"upstage/solar-pro4","source":"aa-api","metric":"aa_time_to_first_token_s","value":1.045,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"aa-api","metric":"aa_output_tokens_per_second","value":411.114,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"aa-api","metric":"aa_time_to_first_token_s","value":0.588,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2.7-code","source":"aa-api","metric":"aa_output_tokens_per_second","value":51.663,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"moonshotai/kimi-k2.7-code","source":"aa-api","metric":"aa_time_to_first_token_s","value":1.211,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"thinkingmachines/inkling-small","source":"aa-api","metric":"aa_output_tokens_per_second","value":173.995,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"thinkingmachines/inkling-small","source":"aa-api","metric":"aa_time_to_first_token_s","value":1.922,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"tencent/hy3","source":"aa-api","metric":"aa_output_tokens_per_second","value":83.637,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"tencent/hy3","source":"aa-api","metric":"aa_time_to_first_token_s","value":1.751,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.7-plus","source":"aa-api","metric":"aa_output_tokens_per_second","value":56.026,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.7-plus","source":"aa-api","metric":"aa_time_to_first_token_s","value":1.677,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"thinkingmachines/inkling","source":"aa-api","metric":"aa_output_tokens_per_second","value":221.085,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Xhigh"},{"modelId":"thinkingmachines/inkling","source":"aa-api","metric":"aa_time_to_first_token_s","value":2.28,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Xhigh"},{"modelId":"upstage/solar-mini4","source":"aa-api","metric":"aa_output_tokens_per_second","value":123.458,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"upstage/solar-mini4","source":"aa-api","metric":"aa_time_to_first_token_s","value":0.966,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"aa-api","metric":"aa_output_tokens_per_second","value":151.897,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Reasoning"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"aa-api","metric":"aa_time_to_first_token_s","value":0.827,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Reasoning"},{"modelId":"google/gemini-3.5-flash-lite","source":"aa-api","metric":"aa_output_tokens_per_second","value":398.034,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"google/gemini-3.5-flash-lite","source":"aa-api","metric":"aa_time_to_first_token_s","value":4.671,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"aa-api","metric":"aa_output_tokens_per_second","value":55.133,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Non-reasoning"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"aa-api","metric":"aa_time_to_first_token_s","value":1.545,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Non-reasoning"},{"modelId":"openai/o3","source":"aa-api","metric":"aa_output_tokens_per_second","value":154.114,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/o3","source":"aa-api","metric":"aa_time_to_first_token_s","value":5.257,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meituan/longcat-2.0","source":"aa-api","metric":"aa_output_tokens_per_second","value":62.3,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meituan/longcat-2.0","source":"aa-api","metric":"aa_time_to_first_token_s","value":1.884,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.6-35b-a3b","source":"aa-api","metric":"aa_output_tokens_per_second","value":133.541,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Reasoning"},{"modelId":"qwen/qwen3.6-35b-a3b","source":"aa-api","metric":"aa_time_to_first_token_s","value":1.199,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Reasoning"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"aa-api","metric":"aa_output_tokens_per_second","value":145.181,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Non-reasoning"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"aa-api","metric":"aa_time_to_first_token_s","value":0.98,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Non-reasoning"},{"modelId":"google/gemma-4-26b-a4b-it","source":"aa-api","metric":"aa_output_tokens_per_second","value":60.709,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Reasoning"},{"modelId":"google/gemma-4-26b-a4b-it","source":"aa-api","metric":"aa_time_to_first_token_s","value":0.672,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Reasoning"},{"modelId":"google/gemma-4-31b-it","source":"aa-api","metric":"aa_output_tokens_per_second","value":35.157,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Reasoning"},{"modelId":"google/gemma-4-31b-it","source":"aa-api","metric":"aa_time_to_first_token_s","value":1.011,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Reasoning"},{"modelId":"mistralai/mistral-medium-3-5","source":"aa-api","metric":"aa_output_tokens_per_second","value":154.231,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"mistralai/mistral-medium-3-5","source":"aa-api","metric":"aa_time_to_first_token_s","value":0.674,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3.5-9b","source":"aa-api","metric":"aa_output_tokens_per_second","value":110.481,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Non-reasoning"},{"modelId":"qwen/qwen3.5-9b","source":"aa-api","metric":"aa_time_to_first_token_s","value":0.421,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Non-reasoning"},{"modelId":"cohere/command-a","source":"aa-api","metric":"aa_output_tokens_per_second","value":165.943,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"cohere/command-a","source":"aa-api","metric":"aa_time_to_first_token_s","value":0.226,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"aa-api","metric":"aa_output_tokens_per_second","value":296.535,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"aa-api","metric":"aa_time_to_first_token_s","value":0.404,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"inception/mercury-2.5","source":"aa-api","metric":"aa_output_tokens_per_second","value":716.049,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"inception/mercury-2.5","source":"aa-api","metric":"aa_time_to_first_token_s","value":2.27,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-oss-120b","source":"aa-api","metric":"aa_output_tokens_per_second","value":259.093,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"High"},{"modelId":"openai/gpt-oss-120b","source":"aa-api","metric":"aa_time_to_first_token_s","value":0.495,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"High"},{"modelId":"mistralai/mistral-small-2603","source":"aa-api","metric":"aa_output_tokens_per_second","value":170.198,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Reasoning"},{"modelId":"mistralai/mistral-small-2603","source":"aa-api","metric":"aa_time_to_first_token_s","value":0.638,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Reasoning"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"aa-api","metric":"aa_output_tokens_per_second","value":163.246,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Reasoning"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"aa-api","metric":"aa_time_to_first_token_s","value":0.471,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Reasoning"},{"modelId":"ibm-granite/granite-4.2-8b","source":"aa-api","metric":"aa_output_tokens_per_second","value":47.867,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"ibm-granite/granite-4.2-8b","source":"aa-api","metric":"aa_time_to_first_token_s","value":0.381,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"arcee-ai/trinity-large-thinking","source":"aa-api","metric":"aa_output_tokens_per_second","value":368.005,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"arcee-ai/trinity-large-thinking","source":"aa-api","metric":"aa_time_to_first_token_s","value":1.101,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"openai/gpt-oss-20b","source":"aa-api","metric":"aa_output_tokens_per_second","value":276.709,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Low"},{"modelId":"openai/gpt-oss-20b","source":"aa-api","metric":"aa_time_to_first_token_s","value":0.384,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Low"},{"modelId":"meta-llama/llama-4-maverick","source":"aa-api","metric":"aa_output_tokens_per_second","value":50.361,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-4-maverick","source":"aa-api","metric":"aa_time_to_first_token_s","value":0.651,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-coder-next","source":"aa-api","metric":"aa_output_tokens_per_second","value":73.083,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"qwen/qwen3-coder-next","source":"aa-api","metric":"aa_time_to_first_token_s","value":0.742,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"nvidia/nemotron-3-nano-30b-a3b","source":"aa-api","metric":"aa_output_tokens_per_second","value":235.162,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Reasoning"},{"modelId":"nvidia/nemotron-3-nano-30b-a3b","source":"aa-api","metric":"aa_time_to_first_token_s","value":0.47,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/","setting":"Reasoning"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"aa-api","metric":"aa_output_tokens_per_second","value":97.351,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"aa-api","metric":"aa_time_to_first_token_s","value":0.63,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-4-scout","source":"aa-api","metric":"aa_output_tokens_per_second","value":131.259,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"meta-llama/llama-4-scout","source":"aa-api","metric":"aa_time_to_first_token_s","value":0.635,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"microsoft/phi-4","source":"aa-api","metric":"aa_output_tokens_per_second","value":45.077,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"microsoft/phi-4","source":"aa-api","metric":"aa_time_to_first_token_s","value":0.984,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-micro-v1","source":"aa-api","metric":"aa_output_tokens_per_second","value":257.394,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"amazon/nova-micro-v1","source":"aa-api","metric":"aa_time_to_first_token_s","value":0.549,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"rekaai/reka-flash-3","source":"aa-api","metric":"aa_output_tokens_per_second","value":86.52,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"rekaai/reka-flash-3","source":"aa-api","metric":"aa_time_to_first_token_s","value":0.797,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://artificialanalysis.ai/"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":54,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/deepseek/deepseek-v4.1-flash-1017/providers","setting":"DeepSeek"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.924,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/deepseek/deepseek-v4.1-flash-1017/providers","setting":"DeepSeek"},{"modelId":"google/gemini-4-argon","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":33,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-4-argon/providers","setting":"Google AI Studio"},{"modelId":"google/gemini-4-argon","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":6.675,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-4-argon/providers","setting":"Google AI Studio"},{"modelId":"meta/muse-wonder","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":73,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/meta/muse-wonder/providers","setting":"Meta"},{"modelId":"meta/muse-wonder","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":2.459,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/meta/muse-wonder/providers","setting":"Meta"},{"modelId":"anthropic/claude-haiku-5.5","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":133,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/anthropic/claude-haiku-5.5/providers","setting":"Anthropic"},{"modelId":"anthropic/claude-haiku-5.5","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.932,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/anthropic/claude-haiku-5.5/providers","setting":"Anthropic"},{"modelId":"google/gemini-nano-banana-2.1","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":30.554,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-nano-banana-2.1/providers","setting":"Google AI Studio"},{"modelId":"mistralai/mistral-large-4-0","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":48,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/mistralai/mistral-large-4-0/providers","setting":"Mistral"},{"modelId":"mistralai/mistral-large-4-0","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.615,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/mistralai/mistral-large-4-0/providers","setting":"Mistral"},{"modelId":"openai/gpt-6.1-sol-pro","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":45,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-6.1-sol-pro/providers","setting":"OpenAI"},{"modelId":"openai/gpt-6.1-sol-pro","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":9.114,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-6.1-sol-pro/providers","setting":"OpenAI"},{"modelId":"openai/gpt-6.1-sol","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":35,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-6.1-sol/providers","setting":"OpenAI"},{"modelId":"openai/gpt-6.1-sol","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":3.138,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-6.1-sol/providers","setting":"OpenAI"},{"modelId":"anthropic/claude-sonnet-5.5","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":99,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/anthropic/claude-sonnet-5.5/providers","setting":"Anthropic"},{"modelId":"anthropic/claude-sonnet-5.5","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.253,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/anthropic/claude-sonnet-5.5/providers","setting":"Anthropic"},{"modelId":"qwen/qwen3.8-max-prime","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":59,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.8-max-prime/providers","setting":"Alibaba"},{"modelId":"qwen/qwen3.8-max-prime","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":2.538,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.8-max-prime/providers","setting":"Alibaba"},{"modelId":"cohere/command-a-plus","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":126,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/cohere/command-a-plus/providers","setting":"Cohere"},{"modelId":"cohere/command-a-plus","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.212,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/cohere/command-a-plus/providers","setting":"Cohere"},{"modelId":"openai/gpt-6-luna-pro","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":76,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-6-luna-pro/providers","setting":"OpenAI"},{"modelId":"openai/gpt-6-luna-pro","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":13.3,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-6-luna-pro/providers","setting":"OpenAI"},{"modelId":"openai/gpt-6-luna","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":58,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-6-luna/providers","setting":"OpenAI"},{"modelId":"openai/gpt-6-luna","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":3.306,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-6-luna/providers","setting":"OpenAI"},{"modelId":"openai/gpt-6-sol-pro","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":65,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-6-sol-pro/providers","setting":"OpenAI"},{"modelId":"openai/gpt-6-sol-pro","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":5.16,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-6-sol-pro/providers","setting":"OpenAI"},{"modelId":"openai/gpt-6-sol","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":56,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-6-sol/providers","setting":"OpenAI"},{"modelId":"openai/gpt-6-sol","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":2.14,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-6-sol/providers","setting":"OpenAI"},{"modelId":"anthropic/claude-opus-5.5","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":68,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/anthropic/claude-opus-5.5/providers","setting":"Anthropic"},{"modelId":"anthropic/claude-opus-5.5","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":4.016,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/anthropic/claude-opus-5.5/providers","setting":"Anthropic"},{"modelId":"xiaomi/mimo-v2.6-pro-ultraspeed","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":126,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/xiaomi/mimo-v2.6-pro-ultraspeed/providers","setting":"Xiaomi"},{"modelId":"xiaomi/mimo-v2.6-pro-ultraspeed","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":3.079,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/xiaomi/mimo-v2.6-pro-ultraspeed/providers","setting":"Xiaomi"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":28,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/xiaomi/mimo-v2.6-flash/providers","setting":"Xiaomi"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":4.54,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/xiaomi/mimo-v2.6-flash/providers","setting":"Xiaomi"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":31,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/xiaomi/mimo-v2.6-pro/providers","setting":"Xiaomi"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":2.989,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/xiaomi/mimo-v2.6-pro/providers","setting":"Xiaomi"},{"modelId":"x-ai/grok-4.7","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":76,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/x-ai/grok-4.7/providers","setting":"xAI"},{"modelId":"x-ai/grok-4.7","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.689,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/x-ai/grok-4.7/providers","setting":"xAI"},{"modelId":"qwen/qwen3.8-omni-flash","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":69,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.8-omni-flash/providers","setting":"Alibaba"},{"modelId":"qwen/qwen3.8-omni-flash","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.895,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.8-omni-flash/providers","setting":"Alibaba"},{"modelId":"z-ai/glm-5.3-flashx","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":96,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/z-ai/glm-5.3-flashx/providers","setting":"Z.AI"},{"modelId":"z-ai/glm-5.3-flashx","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":2.624,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/z-ai/glm-5.3-flashx/providers","setting":"Z.AI"},{"modelId":"openai/gpt-6-astra","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":32,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-6-astra/providers","setting":"OpenAI"},{"modelId":"openai/gpt-6-astra","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":5.216,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-6-astra/providers","setting":"OpenAI"},{"modelId":"openai/gpt-6-astra-pro","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":55.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-6-astra-pro/providers","setting":"OpenAI"},{"modelId":"openai/gpt-6-astra-pro","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":14.525,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-6-astra-pro/providers","setting":"OpenAI"},{"modelId":"qwen/qwen3.8-max-0902","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":37,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.8-max-0902/providers","setting":"Alibaba"},{"modelId":"qwen/qwen3.8-max-0902","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.902,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.8-max-0902/providers","setting":"Alibaba"},{"modelId":"meta/muse-spark-1.3-contributor","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":86,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/meta/muse-spark-1.3-contributor/providers","setting":"Meta"},{"modelId":"meta/muse-spark-1.3-contributor","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":4.005,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/meta/muse-spark-1.3-contributor/providers","setting":"Meta"},{"modelId":"meta/muse-spark-1.3","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":86,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/meta/muse-spark-1.3/providers","setting":"Meta"},{"modelId":"meta/muse-spark-1.3","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":3.408,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/meta/muse-spark-1.3/providers","setting":"Meta"},{"modelId":"google/gemini-3.8-flash","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":82,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-3.8-flash/providers","setting":"Google AI Studio"},{"modelId":"google/gemini-3.8-flash","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":2.37,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-3.8-flash/providers","setting":"Google AI Studio"},{"modelId":"anthropic/claude-fable-5.1","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":59,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/anthropic/claude-fable-5.1/providers","setting":"Anthropic"},{"modelId":"anthropic/claude-fable-5.1","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":2.926,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/anthropic/claude-fable-5.1/providers","setting":"Anthropic"},{"modelId":"qwen/qwen3.8-flash","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":53,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.8-flash/providers","setting":"Alibaba"},{"modelId":"qwen/qwen3.8-flash","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.043,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.8-flash/providers","setting":"Alibaba"},{"modelId":"z-ai/glm-5.3-flash","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":27,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/z-ai/glm-5.3-flash/providers","setting":"Z.AI"},{"modelId":"z-ai/glm-5.3-flash","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":4.383,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/z-ai/glm-5.3-flash/providers","setting":"Z.AI"},{"modelId":"meta/muse-spark-1.2-contributor","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":195,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/meta/muse-spark-1.2-contributor/providers","setting":"Meta"},{"modelId":"meta/muse-spark-1.2-contributor","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.799,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/meta/muse-spark-1.2-contributor/providers","setting":"Meta"},{"modelId":"z-ai/glm-5.3","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":47,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/z-ai/glm-5.3/providers","setting":"Z.AI"},{"modelId":"z-ai/glm-5.3","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":3.167,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/z-ai/glm-5.3/providers","setting":"Z.AI"},{"modelId":"qwen/qwen3.8-27b","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":39,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.8-27b/providers","setting":"Alibaba"},{"modelId":"qwen/qwen3.8-27b","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.674,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.8-27b/providers","setting":"Alibaba"},{"modelId":"google/gemini-3.7-flash","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":88,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-3.7-flash/providers","setting":"Google AI Studio"},{"modelId":"google/gemini-3.7-flash","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":2.443,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-3.7-flash/providers","setting":"Google AI Studio"},{"modelId":"qwen/qwen3.8-2.4t-a95b","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":36,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.8-2.4t-a95b/providers","setting":"Alibaba"},{"modelId":"qwen/qwen3.8-2.4t-a95b","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.293,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.8-2.4t-a95b/providers","setting":"Alibaba"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":30,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/deepseek/deepseek-v4-pro-0813/providers","setting":"DeepSeek"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.001,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/deepseek/deepseek-v4-pro-0813/providers","setting":"DeepSeek"},{"modelId":"x-ai/grok-4.6","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":64,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/x-ai/grok-4.6/providers","setting":"xAI"},{"modelId":"x-ai/grok-4.6","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.806,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/x-ai/grok-4.6/providers","setting":"xAI"},{"modelId":"meta/muse-spark-1.2","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":238,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/meta/muse-spark-1.2/providers","setting":"Meta"},{"modelId":"meta/muse-spark-1.2","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":2.793,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/meta/muse-spark-1.2/providers","setting":"Meta"},{"modelId":"qwen/qwen3.7-flash","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":62,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.7-flash/providers","setting":"Alibaba"},{"modelId":"qwen/qwen3.7-flash","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.719,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.7-flash/providers","setting":"Alibaba"},{"modelId":"anthropic/claude-opus-5","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":56,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/anthropic/claude-opus-5/providers","setting":"Anthropic"},{"modelId":"anthropic/claude-opus-5","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":3.332,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/anthropic/claude-opus-5/providers","setting":"Anthropic"},{"modelId":"google/gemini-3.6-flash","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":113,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-3.6-flash/providers","setting":"Google AI Studio"},{"modelId":"google/gemini-3.6-flash","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.334,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-3.6-flash/providers","setting":"Google AI Studio"},{"modelId":"google/gemini-3.5-flash-lite","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":120,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-3.5-flash-lite/providers","setting":"Google AI Studio"},{"modelId":"google/gemini-3.5-flash-lite","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.696,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-3.5-flash-lite/providers","setting":"Google AI Studio"},{"modelId":"meta/muse-spark-1.1","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":245,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/meta/muse-spark-1.1/providers","setting":"Meta"},{"modelId":"meta/muse-spark-1.1","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.933,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/meta/muse-spark-1.1/providers","setting":"Meta"},{"modelId":"openai/gpt-5.6-luna-pro","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":104,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5.6-luna-pro/providers","setting":"OpenAI"},{"modelId":"openai/gpt-5.6-luna-pro","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":5.436,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5.6-luna-pro/providers","setting":"OpenAI"},{"modelId":"openai/gpt-5.6-luna","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":69,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5.6-luna/providers","setting":"OpenAI"},{"modelId":"openai/gpt-5.6-luna","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.958,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5.6-luna/providers","setting":"OpenAI"},{"modelId":"openai/gpt-5.6-terra-pro","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":89.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5.6-terra-pro/providers","setting":"OpenAI"},{"modelId":"openai/gpt-5.6-terra-pro","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":2.79,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5.6-terra-pro/providers","setting":"OpenAI"},{"modelId":"openai/gpt-5.6-terra","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":77,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5.6-terra/providers","setting":"OpenAI"},{"modelId":"openai/gpt-5.6-terra","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":2.049,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5.6-terra/providers","setting":"OpenAI"},{"modelId":"openai/gpt-5.6-sol-pro","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":148,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5.6-sol-pro/providers","setting":"OpenAI"},{"modelId":"openai/gpt-5.6-sol-pro","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":5.656,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5.6-sol-pro/providers","setting":"OpenAI"},{"modelId":"openai/gpt-5.6-sol","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":88,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5.6-sol/providers","setting":"OpenAI"},{"modelId":"openai/gpt-5.6-sol","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":2.233,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5.6-sol/providers","setting":"OpenAI"},{"modelId":"x-ai/grok-4.5","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":54,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/x-ai/grok-4.5/providers","setting":"xAI"},{"modelId":"x-ai/grok-4.5","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.566,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/x-ai/grok-4.5/providers","setting":"xAI"},{"modelId":"anthropic/claude-sonnet-5","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":61,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/anthropic/claude-sonnet-5/providers","setting":"Anthropic"},{"modelId":"anthropic/claude-sonnet-5","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":2.221,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/anthropic/claude-sonnet-5/providers","setting":"Anthropic"},{"modelId":"google/gemini-3.1-flash-lite-image","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":7.011,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-3.1-flash-lite-image/providers","setting":"Google AI Studio"},{"modelId":"google/gemini-3.1-flash-image","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":16.319,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-3.1-flash-image/providers","setting":"Google AI Studio"},{"modelId":"google/gemini-3-pro-image","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":33.492,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-3-pro-image/providers","setting":"Google AI Studio"},{"modelId":"z-ai/glm-5.2","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":46,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/z-ai/glm-5.2/providers","setting":"Z.AI"},{"modelId":"z-ai/glm-5.2","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":2.412,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/z-ai/glm-5.2/providers","setting":"Z.AI"},{"modelId":"moonshotai/kimi-k2.7-code","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":35.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/moonshotai/kimi-k2.7-code/providers","setting":"Moonshot AI"},{"modelId":"moonshotai/kimi-k2.7-code","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":2.069,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/moonshotai/kimi-k2.7-code/providers","setting":"Moonshot AI"},{"modelId":"anthropic/claude-fable-5","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":50,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/anthropic/claude-fable-5/providers","setting":"Anthropic"},{"modelId":"anthropic/claude-fable-5","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":4.731,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/anthropic/claude-fable-5/providers","setting":"Anthropic"},{"modelId":"qwen/qwen3.7-plus","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":56,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.7-plus/providers","setting":"Alibaba"},{"modelId":"qwen/qwen3.7-plus","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.249,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.7-plus/providers","setting":"Alibaba"},{"modelId":"minimax/minimax-m3","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":62,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/minimax/minimax-m3/providers","setting":"Minimax"},{"modelId":"minimax/minimax-m3","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.442,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/minimax/minimax-m3/providers","setting":"Minimax"},{"modelId":"anthropic/claude-opus-4.8","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":65,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/anthropic/claude-opus-4.8/providers","setting":"Anthropic"},{"modelId":"anthropic/claude-opus-4.8","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.187,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/anthropic/claude-opus-4.8/providers","setting":"Anthropic"},{"modelId":"qwen/qwen3.7-max","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":69,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.7-max/providers","setting":"Alibaba"},{"modelId":"qwen/qwen3.7-max","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.166,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.7-max/providers","setting":"Alibaba"},{"modelId":"x-ai/grok-build-0.1","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":151,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/x-ai/grok-build-0.1/providers","setting":"xAI"},{"modelId":"x-ai/grok-build-0.1","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.223,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/x-ai/grok-build-0.1/providers","setting":"xAI"},{"modelId":"google/gemini-3.5-flash","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":219,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-3.5-flash/providers","setting":"Google AI Studio"},{"modelId":"google/gemini-3.5-flash","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.676,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-3.5-flash/providers","setting":"Google AI Studio"},{"modelId":"google/gemini-3.1-flash-lite","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":118,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-3.1-flash-lite/providers","setting":"Google AI Studio"},{"modelId":"google/gemini-3.1-flash-lite","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.731,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-3.1-flash-lite/providers","setting":"Google AI Studio"},{"modelId":"openai/gpt-chat-latest","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":62,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-chat-latest/providers","setting":"OpenAI"},{"modelId":"openai/gpt-chat-latest","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-chat-latest/providers","setting":"OpenAI"},{"modelId":"x-ai/grok-4.3","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":58,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/x-ai/grok-4.3/providers","setting":"xAI"},{"modelId":"x-ai/grok-4.3","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.336,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/x-ai/grok-4.3/providers","setting":"xAI"},{"modelId":"mistralai/mistral-medium-3-5","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":142,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/mistralai/mistral-medium-3-5/providers","setting":"Mistral"},{"modelId":"mistralai/mistral-medium-3-5","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.349,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/mistralai/mistral-medium-3-5/providers","setting":"Mistral"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":46,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.5-plus-20260420/providers","setting":"Alibaba"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.61,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.5-plus-20260420/providers","setting":"Alibaba"},{"modelId":"qwen/qwen3.6-flash","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":89,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.6-flash/providers","setting":"Alibaba"},{"modelId":"qwen/qwen3.6-flash","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.523,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.6-flash/providers","setting":"Alibaba"},{"modelId":"qwen/qwen3.6-27b","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":51,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.6-27b/providers","setting":"Alibaba"},{"modelId":"qwen/qwen3.6-27b","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.789,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.6-27b/providers","setting":"Alibaba"},{"modelId":"openai/gpt-5.5-pro","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":28.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5.5-pro/providers","setting":"OpenAI"},{"modelId":"openai/gpt-5.5-pro","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":3.882,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5.5-pro/providers","setting":"OpenAI"},{"modelId":"openai/gpt-5.5","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":63,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5.5/providers","setting":"OpenAI"},{"modelId":"openai/gpt-5.5","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":3.387,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5.5/providers","setting":"OpenAI"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":33,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/xiaomi/mimo-v2.5-pro/providers","setting":"Xiaomi"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.957,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/xiaomi/mimo-v2.5-pro/providers","setting":"Xiaomi"},{"modelId":"xiaomi/mimo-v2.5","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":27,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/xiaomi/mimo-v2.5/providers","setting":"Xiaomi"},{"modelId":"xiaomi/mimo-v2.5","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":3.077,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/xiaomi/mimo-v2.5/providers","setting":"Xiaomi"},{"modelId":"openai/gpt-5.4-image-2","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":67.451,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5.4-image-2/providers","setting":"OpenAI"},{"modelId":"moonshotai/kimi-k2.6","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":34,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/moonshotai/kimi-k2.6/providers","setting":"Moonshot AI"},{"modelId":"moonshotai/kimi-k2.6","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.541,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/moonshotai/kimi-k2.6/providers","setting":"Moonshot AI"},{"modelId":"anthropic/claude-opus-4.7","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":45,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/anthropic/claude-opus-4.7/providers","setting":"Anthropic"},{"modelId":"anthropic/claude-opus-4.7","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.754,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/anthropic/claude-opus-4.7/providers","setting":"Anthropic"},{"modelId":"z-ai/glm-5.1","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":25,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/z-ai/glm-5.1/providers","setting":"Z.AI"},{"modelId":"z-ai/glm-5.1","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":9.252,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/z-ai/glm-5.1/providers","setting":"Z.AI"},{"modelId":"qwen/qwen3.6-plus","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":43,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.6-plus/providers","setting":"Alibaba"},{"modelId":"qwen/qwen3.6-plus","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.6-plus/providers","setting":"Alibaba"},{"modelId":"z-ai/glm-5v-turbo","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":32,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/z-ai/glm-5v-turbo/providers","setting":"Z.AI"},{"modelId":"z-ai/glm-5v-turbo","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":2.743,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/z-ai/glm-5v-turbo/providers","setting":"Z.AI"},{"modelId":"x-ai/grok-4.20-multi-agent","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":337,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/x-ai/grok-4.20-multi-agent/providers","setting":"xAI"},{"modelId":"x-ai/grok-4.20-multi-agent","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":8.483,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/x-ai/grok-4.20-multi-agent/providers","setting":"xAI"},{"modelId":"x-ai/grok-4.20","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":81,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/x-ai/grok-4.20/providers","setting":"xAI"},{"modelId":"x-ai/grok-4.20","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.688,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/x-ai/grok-4.20/providers","setting":"xAI"},{"modelId":"google/lyria-3-pro-preview","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":22.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/lyria-3-pro-preview/providers","setting":"Google AI Studio"},{"modelId":"google/lyria-3-pro-preview","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":3.179,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/lyria-3-pro-preview/providers","setting":"Google AI Studio"},{"modelId":"google/lyria-3-clip-preview","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":8,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/lyria-3-clip-preview/providers","setting":"Google AI Studio"},{"modelId":"google/lyria-3-clip-preview","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":2.516,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/lyria-3-clip-preview/providers","setting":"Google AI Studio"},{"modelId":"minimax/minimax-m2.7","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":43,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/minimax/minimax-m2.7/providers","setting":"Minimax"},{"modelId":"minimax/minimax-m2.7","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.902,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/minimax/minimax-m2.7/providers","setting":"Minimax"},{"modelId":"openai/gpt-5.4-nano","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":92,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5.4-nano/providers","setting":"OpenAI"},{"modelId":"openai/gpt-5.4-nano","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.923,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5.4-nano/providers","setting":"OpenAI"},{"modelId":"openai/gpt-5.4-mini","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":99,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5.4-mini/providers","setting":"OpenAI"},{"modelId":"openai/gpt-5.4-mini","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.976,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5.4-mini/providers","setting":"OpenAI"},{"modelId":"mistralai/mistral-small-2603","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":109,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/mistralai/mistral-small-2603/providers","setting":"Mistral"},{"modelId":"mistralai/mistral-small-2603","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.357,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/mistralai/mistral-small-2603/providers","setting":"Mistral"},{"modelId":"z-ai/glm-5-turbo","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":23,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/z-ai/glm-5-turbo/providers","setting":"Z.AI"},{"modelId":"z-ai/glm-5-turbo","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":7.433,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/z-ai/glm-5-turbo/providers","setting":"Z.AI"},{"modelId":"openai/gpt-5.4-pro","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":16,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5.4-pro/providers","setting":"OpenAI"},{"modelId":"openai/gpt-5.4-pro","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":8.973,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5.4-pro/providers","setting":"OpenAI"},{"modelId":"openai/gpt-5.4","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":62,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5.4/providers","setting":"OpenAI"},{"modelId":"openai/gpt-5.4","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.312,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5.4/providers","setting":"OpenAI"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":203,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-3.1-flash-lite-preview/providers","setting":"Google AI Studio"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.645,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-3.1-flash-lite-preview/providers","setting":"Google AI Studio"},{"modelId":"google/gemini-3.1-flash-image-preview","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":17.736,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-3.1-flash-image-preview/providers","setting":"Google AI Studio"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":116,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.5-35b-a3b/providers","setting":"Alibaba"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.399,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.5-35b-a3b/providers","setting":"Alibaba"},{"modelId":"qwen/qwen3.5-27b","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":70.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.5-27b/providers","setting":"Alibaba"},{"modelId":"qwen/qwen3.5-27b","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.184,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.5-27b/providers","setting":"Alibaba"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":159.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.5-122b-a10b/providers","setting":"Alibaba"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.477,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.5-122b-a10b/providers","setting":"Alibaba"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":91,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.5-flash-02-23/providers","setting":"Alibaba"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.604,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.5-flash-02-23/providers","setting":"Alibaba"},{"modelId":"google/gemini-3.1-pro-preview-customtools","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":125,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-3.1-pro-preview-customtools/providers","setting":"Google AI Studio"},{"modelId":"google/gemini-3.1-pro-preview-customtools","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":2.679,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-3.1-pro-preview-customtools/providers","setting":"Google AI Studio"},{"modelId":"openai/gpt-5.3-codex","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":78,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5.3-codex/providers","setting":"OpenAI"},{"modelId":"openai/gpt-5.3-codex","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":2.526,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5.3-codex/providers","setting":"OpenAI"},{"modelId":"google/gemini-3.1-pro-preview","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":107,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-3.1-pro-preview/providers","setting":"Google AI Studio"},{"modelId":"google/gemini-3.1-pro-preview","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":4.065,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-3.1-pro-preview/providers","setting":"Google AI Studio"},{"modelId":"anthropic/claude-sonnet-4.6","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":39,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/anthropic/claude-sonnet-4.6/providers","setting":"Anthropic"},{"modelId":"anthropic/claude-sonnet-4.6","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.004,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/anthropic/claude-sonnet-4.6/providers","setting":"Anthropic"},{"modelId":"qwen/qwen3.5-plus-02-15","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":54,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.5-plus-02-15/providers","setting":"Alibaba"},{"modelId":"qwen/qwen3.5-plus-02-15","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.312,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.5-plus-02-15/providers","setting":"Alibaba"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":54,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.5-397b-a17b/providers","setting":"Alibaba"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.547,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3.5-397b-a17b/providers","setting":"Alibaba"},{"modelId":"minimax/minimax-m2.5","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":39,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/minimax/minimax-m2.5/providers","setting":"Minimax"},{"modelId":"minimax/minimax-m2.5","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.096,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/minimax/minimax-m2.5/providers","setting":"Minimax"},{"modelId":"z-ai/glm-5","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":46,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/z-ai/glm-5/providers","setting":"Z.AI"},{"modelId":"z-ai/glm-5","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":8.214,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/z-ai/glm-5/providers","setting":"Z.AI"},{"modelId":"anthropic/claude-opus-4.6","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":34,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/anthropic/claude-opus-4.6/providers","setting":"Anthropic"},{"modelId":"anthropic/claude-opus-4.6","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.819,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/anthropic/claude-opus-4.6/providers","setting":"Anthropic"},{"modelId":"minimax/minimax-m2-her","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":68,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/minimax/minimax-m2-her/providers","setting":"Minimax"},{"modelId":"minimax/minimax-m2-her","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.711,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/minimax/minimax-m2-her/providers","setting":"Minimax"},{"modelId":"openai/gpt-audio","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":85,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-audio/providers","setting":"OpenAI"},{"modelId":"openai/gpt-audio","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.724,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-audio/providers","setting":"OpenAI"},{"modelId":"openai/gpt-audio-mini","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":121,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-audio-mini/providers","setting":"OpenAI"},{"modelId":"openai/gpt-audio-mini","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.448,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-audio-mini/providers","setting":"OpenAI"},{"modelId":"minimax/minimax-m2.1","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":31,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/minimax/minimax-m2.1/providers","setting":"Minimax"},{"modelId":"minimax/minimax-m2.1","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.735,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/minimax/minimax-m2.1/providers","setting":"Minimax"},{"modelId":"z-ai/glm-4.7","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/z-ai/glm-4.7/providers","setting":"Z.AI"},{"modelId":"z-ai/glm-4.7","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":8.98,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/z-ai/glm-4.7/providers","setting":"Z.AI"},{"modelId":"google/gemini-3-flash-preview","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":80,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-3-flash-preview/providers","setting":"Google AI Studio"},{"modelId":"google/gemini-3-flash-preview","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.686,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-3-flash-preview/providers","setting":"Google AI Studio"},{"modelId":"openai/gpt-5.2-pro","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":20.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5.2-pro/providers","setting":"OpenAI"},{"modelId":"openai/gpt-5.2-pro","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":6.951,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5.2-pro/providers","setting":"OpenAI"},{"modelId":"openai/gpt-5.2","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":56,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5.2/providers","setting":"OpenAI"},{"modelId":"openai/gpt-5.2","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":2.868,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5.2/providers","setting":"OpenAI"},{"modelId":"mistralai/devstral-2512","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":97,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/mistralai/devstral-2512/providers","setting":"Mistral"},{"modelId":"mistralai/devstral-2512","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.005,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/mistralai/devstral-2512/providers","setting":"Mistral"},{"modelId":"z-ai/glm-4.6v","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":35.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/z-ai/glm-4.6v/providers","setting":"Z.AI"},{"modelId":"z-ai/glm-4.6v","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":3.246,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/z-ai/glm-4.6v/providers","setting":"Z.AI"},{"modelId":"mistralai/ministral-14b-2512","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":63,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/mistralai/ministral-14b-2512/providers","setting":"Mistral"},{"modelId":"mistralai/ministral-14b-2512","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.396,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/mistralai/ministral-14b-2512/providers","setting":"Mistral"},{"modelId":"mistralai/ministral-8b-2512","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":71,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/mistralai/ministral-8b-2512/providers","setting":"Mistral"},{"modelId":"mistralai/ministral-8b-2512","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.361,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/mistralai/ministral-8b-2512/providers","setting":"Mistral"},{"modelId":"mistralai/ministral-3b-2512","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":130,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/mistralai/ministral-3b-2512/providers","setting":"Mistral"},{"modelId":"mistralai/ministral-3b-2512","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.307,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/mistralai/ministral-3b-2512/providers","setting":"Mistral"},{"modelId":"mistralai/mistral-large-2512","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":66,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/mistralai/mistral-large-2512/providers","setting":"Mistral"},{"modelId":"mistralai/mistral-large-2512","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.53,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/mistralai/mistral-large-2512/providers","setting":"Mistral"},{"modelId":"anthropic/claude-opus-4.5","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":46,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/anthropic/claude-opus-4.5/providers","setting":"Anthropic"},{"modelId":"anthropic/claude-opus-4.5","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.088,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/anthropic/claude-opus-4.5/providers","setting":"Anthropic"},{"modelId":"google/gemini-3-pro-image-preview","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":24.421,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-3-pro-image-preview/providers","setting":"Google AI Studio"},{"modelId":"openai/gpt-5.1","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":45,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5.1/providers","setting":"OpenAI"},{"modelId":"openai/gpt-5.1","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.344,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5.1/providers","setting":"OpenAI"},{"modelId":"mistralai/voxtral-small-24b-2507","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":57,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/mistralai/voxtral-small-24b-2507/providers","setting":"Mistral"},{"modelId":"mistralai/voxtral-small-24b-2507","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.747,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/mistralai/voxtral-small-24b-2507/providers","setting":"Mistral"},{"modelId":"minimax/minimax-m2","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":43,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/minimax/minimax-m2/providers","setting":"Minimax"},{"modelId":"minimax/minimax-m2","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.921,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/minimax/minimax-m2/providers","setting":"Minimax"},{"modelId":"openai/gpt-5-image-mini","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":41.781,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5-image-mini/providers","setting":"OpenAI"},{"modelId":"anthropic/claude-haiku-4.5","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":68,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/anthropic/claude-haiku-4.5/providers","setting":"Anthropic"},{"modelId":"anthropic/claude-haiku-4.5","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.516,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/anthropic/claude-haiku-4.5/providers","setting":"Anthropic"},{"modelId":"openai/gpt-5-image","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":16.092,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5-image/providers","setting":"OpenAI"},{"modelId":"openai/gpt-5-pro","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":11,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5-pro/providers","setting":"OpenAI"},{"modelId":"openai/gpt-5-pro","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":38.582,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5-pro/providers","setting":"OpenAI"},{"modelId":"z-ai/glm-4.6","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":26,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/z-ai/glm-4.6/providers","setting":"Z.AI"},{"modelId":"z-ai/glm-4.6","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":6.382,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/z-ai/glm-4.6/providers","setting":"Z.AI"},{"modelId":"anthropic/claude-sonnet-4.5","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":39,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/anthropic/claude-sonnet-4.5/providers","setting":"Anthropic"},{"modelId":"anthropic/claude-sonnet-4.5","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.051,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/anthropic/claude-sonnet-4.5/providers","setting":"Anthropic"},{"modelId":"qwen/qwen3-coder-flash","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":75,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3-coder-flash/providers","setting":"Alibaba"},{"modelId":"qwen/qwen3-coder-flash","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.886,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen3-coder-flash/providers","setting":"Alibaba"},{"modelId":"mistralai/mistral-medium-3.1","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":90,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/mistralai/mistral-medium-3.1/providers","setting":"Mistral"},{"modelId":"mistralai/mistral-medium-3.1","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.43,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/mistralai/mistral-medium-3.1/providers","setting":"Mistral"},{"modelId":"z-ai/glm-4.5v","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":60,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/z-ai/glm-4.5v/providers","setting":"Z.AI"},{"modelId":"z-ai/glm-4.5v","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":2.591,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/z-ai/glm-4.5v/providers","setting":"Z.AI"},{"modelId":"openai/gpt-5-mini","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":82,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5-mini/providers","setting":"OpenAI"},{"modelId":"openai/gpt-5-mini","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":3.76,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5-mini/providers","setting":"OpenAI"},{"modelId":"openai/gpt-5-nano","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":77,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5-nano/providers","setting":"OpenAI"},{"modelId":"openai/gpt-5-nano","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.129,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-5-nano/providers","setting":"OpenAI"},{"modelId":"mistralai/codestral-2508","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":111.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/mistralai/codestral-2508/providers","setting":"Mistral"},{"modelId":"mistralai/codestral-2508","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.427,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/mistralai/codestral-2508/providers","setting":"Mistral"},{"modelId":"z-ai/glm-4.5","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":25,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/z-ai/glm-4.5/providers","setting":"Z.AI"},{"modelId":"z-ai/glm-4.5","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":8.583,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/z-ai/glm-4.5/providers","setting":"Z.AI"},{"modelId":"z-ai/glm-4.5-air","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":66.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/z-ai/glm-4.5-air/providers","setting":"Z.AI"},{"modelId":"z-ai/glm-4.5-air","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.52,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/z-ai/glm-4.5-air/providers","setting":"Z.AI"},{"modelId":"google/gemini-2.5-flash-lite","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":130,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-2.5-flash-lite/providers","setting":"Google AI Studio"},{"modelId":"google/gemini-2.5-flash-lite","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.59,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-2.5-flash-lite/providers","setting":"Google AI Studio"},{"modelId":"mistralai/mistral-small-3.2-24b-instruct","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":140,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/mistralai/mistral-small-3.2-24b-instruct/providers","setting":"Mistral"},{"modelId":"mistralai/mistral-small-3.2-24b-instruct","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":2.375,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/mistralai/mistral-small-3.2-24b-instruct/providers","setting":"Mistral"},{"modelId":"minimax/minimax-m1","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":32.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/minimax/minimax-m1/providers","setting":"Minimax"},{"modelId":"minimax/minimax-m1","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.998,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/minimax/minimax-m1/providers","setting":"Minimax"},{"modelId":"google/gemini-2.5-flash","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":78,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-2.5-flash/providers","setting":"Google AI Studio"},{"modelId":"google/gemini-2.5-flash","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.599,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-2.5-flash/providers","setting":"Google AI Studio"},{"modelId":"google/gemini-2.5-pro","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":83,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-2.5-pro/providers","setting":"Google AI Studio"},{"modelId":"google/gemini-2.5-pro","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":3.718,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-2.5-pro/providers","setting":"Google AI Studio"},{"modelId":"google/gemini-2.5-pro-preview","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":83,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-2.5-pro-preview/providers","setting":"Google AI Studio"},{"modelId":"google/gemini-2.5-pro-preview","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":3.718,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/google/gemini-2.5-pro-preview/providers","setting":"Google AI Studio"},{"modelId":"mistralai/mistral-medium-3","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":134,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/mistralai/mistral-medium-3/providers","setting":"Mistral"},{"modelId":"mistralai/mistral-medium-3","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.315,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/mistralai/mistral-medium-3/providers","setting":"Mistral"},{"modelId":"openai/o4-mini-high","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":143,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/o4-mini-high/providers","setting":"OpenAI"},{"modelId":"openai/o4-mini-high","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":5.084,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/o4-mini-high/providers","setting":"OpenAI"},{"modelId":"openai/o3","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":59,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/o3/providers","setting":"OpenAI"},{"modelId":"openai/o3","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":1.938,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/o3/providers","setting":"OpenAI"},{"modelId":"openai/o4-mini","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":121,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/o4-mini/providers","setting":"OpenAI"},{"modelId":"openai/o4-mini","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":2.377,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/o4-mini/providers","setting":"OpenAI"},{"modelId":"openai/gpt-4.1","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":76,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-4.1/providers","setting":"OpenAI"},{"modelId":"openai/gpt-4.1","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.808,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-4.1/providers","setting":"OpenAI"},{"modelId":"openai/gpt-4.1-mini","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":80,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-4.1-mini/providers","setting":"OpenAI"},{"modelId":"openai/gpt-4.1-mini","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.882,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-4.1-mini/providers","setting":"OpenAI"},{"modelId":"openai/gpt-4.1-nano","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":84,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-4.1-nano/providers","setting":"OpenAI"},{"modelId":"openai/gpt-4.1-nano","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.763,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-4.1-nano/providers","setting":"OpenAI"},{"modelId":"cohere/command-a","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":65,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/cohere/command-a/providers","setting":"Cohere"},{"modelId":"cohere/command-a","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.254,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/cohere/command-a/providers","setting":"Cohere"},{"modelId":"mistralai/mistral-saba","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":92,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/mistralai/mistral-saba/providers","setting":"Mistral"},{"modelId":"mistralai/mistral-saba","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.441,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/mistralai/mistral-saba/providers","setting":"Mistral"},{"modelId":"openai/o3-mini-high","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":111,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/o3-mini-high/providers","setting":"OpenAI"},{"modelId":"openai/o3-mini-high","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":2.706,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/o3-mini-high/providers","setting":"OpenAI"},{"modelId":"qwen/qwen-plus","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":50,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen-plus/providers","setting":"Alibaba"},{"modelId":"qwen/qwen-plus","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.462,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/qwen/qwen-plus/providers","setting":"Alibaba"},{"modelId":"openai/o3-mini","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":153.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/o3-mini/providers","setting":"OpenAI"},{"modelId":"openai/o3-mini","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":2.656,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/o3-mini/providers","setting":"OpenAI"},{"modelId":"minimax/minimax-01","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":25,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/minimax/minimax-01/providers","setting":"Minimax"},{"modelId":"minimax/minimax-01","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.739,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/minimax/minimax-01/providers","setting":"Minimax"},{"modelId":"openai/o1","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":76,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/o1/providers","setting":"OpenAI"},{"modelId":"openai/o1","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.946,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/o1/providers","setting":"OpenAI"},{"modelId":"cohere/command-r7b-12-2024","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":61.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/cohere/command-r7b-12-2024/providers","setting":"Cohere"},{"modelId":"cohere/command-r7b-12-2024","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.187,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/cohere/command-r7b-12-2024/providers","setting":"Cohere"},{"modelId":"openai/gpt-4o-2024-11-20","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":79,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-4o-2024-11-20/providers","setting":"OpenAI"},{"modelId":"openai/gpt-4o-2024-11-20","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.561,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-4o-2024-11-20/providers","setting":"OpenAI"},{"modelId":"mistralai/mistral-large-2407","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":45,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/mistralai/mistral-large-2407/providers","setting":"Mistral"},{"modelId":"mistralai/mistral-large-2407","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.573,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/mistralai/mistral-large-2407/providers","setting":"Mistral"},{"modelId":"cohere/command-r-08-2024","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":27,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/cohere/command-r-08-2024/providers","setting":"Cohere"},{"modelId":"cohere/command-r-08-2024","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.246,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/cohere/command-r-08-2024/providers","setting":"Cohere"},{"modelId":"cohere/command-r-plus-08-2024","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":31,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/cohere/command-r-plus-08-2024/providers","setting":"Cohere"},{"modelId":"cohere/command-r-plus-08-2024","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.282,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/cohere/command-r-plus-08-2024/providers","setting":"Cohere"},{"modelId":"openai/gpt-4o-2024-08-06","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":63,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-4o-2024-08-06/providers","setting":"OpenAI"},{"modelId":"openai/gpt-4o-2024-08-06","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.666,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-4o-2024-08-06/providers","setting":"OpenAI"},{"modelId":"openai/gpt-4o-mini","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":95,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-4o-mini/providers","setting":"OpenAI"},{"modelId":"openai/gpt-4o-mini","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.552,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-4o-mini/providers","setting":"OpenAI"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":99,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-4o-mini-2024-07-18/providers","setting":"OpenAI"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.58,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-4o-mini-2024-07-18/providers","setting":"OpenAI"},{"modelId":"openai/gpt-4o","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":73,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-4o/providers","setting":"OpenAI"},{"modelId":"openai/gpt-4o","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.615,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-4o/providers","setting":"OpenAI"},{"modelId":"openai/gpt-4o-2024-05-13","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":55,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-4o-2024-05-13/providers","setting":"OpenAI"},{"modelId":"openai/gpt-4o-2024-05-13","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.545,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-4o-2024-05-13/providers","setting":"OpenAI"},{"modelId":"mistralai/mixtral-8x22b-instruct","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":145,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/mistralai/mixtral-8x22b-instruct/providers","setting":"Mistral"},{"modelId":"mistralai/mixtral-8x22b-instruct","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.397,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/mistralai/mixtral-8x22b-instruct/providers","setting":"Mistral"},{"modelId":"openai/gpt-4-turbo","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":48,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-4-turbo/providers","setting":"OpenAI"},{"modelId":"openai/gpt-4-turbo","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.723,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-4-turbo/providers","setting":"OpenAI"},{"modelId":"mistralai/mistral-large","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":74,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/mistralai/mistral-large/providers","setting":"Mistral"},{"modelId":"mistralai/mistral-large","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.448,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/mistralai/mistral-large/providers","setting":"Mistral"},{"modelId":"openai/gpt-3.5-turbo","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":73,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-3.5-turbo/providers","setting":"OpenAI"},{"modelId":"openai/gpt-3.5-turbo","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.761,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-3.5-turbo/providers","setting":"OpenAI"},{"modelId":"openai/gpt-4","source":"openrouter-speed","metric":"or_output_tokens_per_second","value":54,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-4/providers","setting":"OpenAI"},{"modelId":"openai/gpt-4","source":"openrouter-speed","metric":"or_time_to_first_token_s","value":0.891,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://openrouter.ai/openai/gpt-4/providers","setting":"OpenAI"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"huggingface","metric":"hf_downloads_30d","value":17924,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"huggingface","metric":"hf_likes","value":1724,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"huggingface","metric":"hf_trending","value":1564,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"huggingface","metric":"hf_downloads_all_time","value":17924,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"huggingface","metric":"hf_parameters","value":763205315794,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017"},{"modelId":"reflection/beam-1.0-501b-a23b","source":"huggingface","metric":"hf_downloads_30d","value":2097,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/reflection/Beam-1.0-501B-A23B"},{"modelId":"reflection/beam-1.0-501b-a23b","source":"huggingface","metric":"hf_likes","value":170,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/reflection/Beam-1.0-501B-A23B"},{"modelId":"reflection/beam-1.0-501b-a23b","source":"huggingface","metric":"hf_trending","value":168,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/reflection/Beam-1.0-501B-A23B"},{"modelId":"reflection/beam-1.0-501b-a23b","source":"huggingface","metric":"hf_downloads_all_time","value":2097,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/reflection/Beam-1.0-501B-A23B"},{"modelId":"reflection/beam-1.0-501b-a23b","source":"huggingface","metric":"hf_parameters","value":501267612352,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/reflection/Beam-1.0-501B-A23B"},{"modelId":"moondream/moondream3-preview","source":"huggingface","metric":"hf_downloads_30d","value":85120,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moondream/moondream3-preview"},{"modelId":"moondream/moondream3-preview","source":"huggingface","metric":"hf_likes","value":692,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moondream/moondream3-preview"},{"modelId":"moondream/moondream3-preview","source":"huggingface","metric":"hf_trending","value":3,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moondream/moondream3-preview"},{"modelId":"moondream/moondream3-preview","source":"huggingface","metric":"hf_downloads_all_time","value":1400799,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moondream/moondream3-preview"},{"modelId":"moondream/moondream3-preview","source":"huggingface","metric":"hf_parameters","value":9268626928,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moondream/moondream3-preview"},{"modelId":"moondream/moondream3.1-9b-a2b","source":"huggingface","metric":"hf_downloads_30d","value":12658,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moondream/moondream3.1-9B-A2B"},{"modelId":"moondream/moondream3.1-9b-a2b","source":"huggingface","metric":"hf_likes","value":89,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moondream/moondream3.1-9B-A2B"},{"modelId":"moondream/moondream3.1-9b-a2b","source":"huggingface","metric":"hf_trending","value":11,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moondream/moondream3.1-9B-A2B"},{"modelId":"moondream/moondream3.1-9b-a2b","source":"huggingface","metric":"hf_downloads_all_time","value":44348,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moondream/moondream3.1-9B-A2B"},{"modelId":"moondream/moondream3.1-9b-a2b","source":"huggingface","metric":"hf_parameters","value":9273869808,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moondream/moondream3.1-9B-A2B"},{"modelId":"meta/muse-spark-open","source":"huggingface","metric":"hf_downloads_30d","value":2109,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-models/Muse-Spark-Open-816B-A42B"},{"modelId":"meta/muse-spark-open","source":"huggingface","metric":"hf_likes","value":584,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-models/Muse-Spark-Open-816B-A42B"},{"modelId":"meta/muse-spark-open","source":"huggingface","metric":"hf_trending","value":535,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-models/Muse-Spark-Open-816B-A42B"},{"modelId":"meta/muse-spark-open","source":"huggingface","metric":"hf_downloads_all_time","value":2312,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-models/Muse-Spark-Open-816B-A42B"},{"modelId":"meta/muse-spark-open","source":"huggingface","metric":"hf_parameters","value":822036529664,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-models/Muse-Spark-Open-816B-A42B"},{"modelId":"liquid/lfm-2.5-24b-a2b","source":"huggingface","metric":"hf_downloads_30d","value":14151,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/LiquidAI/LFM2.5-24B-A2B"},{"modelId":"liquid/lfm-2.5-24b-a2b","source":"huggingface","metric":"hf_likes","value":501,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/LiquidAI/LFM2.5-24B-A2B"},{"modelId":"liquid/lfm-2.5-24b-a2b","source":"huggingface","metric":"hf_trending","value":485,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/LiquidAI/LFM2.5-24B-A2B"},{"modelId":"liquid/lfm-2.5-24b-a2b","source":"huggingface","metric":"hf_downloads_all_time","value":14151,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/LiquidAI/LFM2.5-24B-A2B"},{"modelId":"liquid/lfm-2.5-24b-a2b","source":"huggingface","metric":"hf_parameters","value":23971585280,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/LiquidAI/LFM2.5-24B-A2B"},{"modelId":"stepfun/step-5-preview","source":"huggingface","metric":"hf_downloads_30d","value":1430,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/stepfun-ai/Step-5-Preview"},{"modelId":"stepfun/step-5-preview","source":"huggingface","metric":"hf_likes","value":117,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/stepfun-ai/Step-5-Preview"},{"modelId":"stepfun/step-5-preview","source":"huggingface","metric":"hf_trending","value":116,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/stepfun-ai/Step-5-Preview"},{"modelId":"stepfun/step-5-preview","source":"huggingface","metric":"hf_downloads_all_time","value":1430,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/stepfun-ai/Step-5-Preview"},{"modelId":"stepfun/step-5-preview","source":"huggingface","metric":"hf_parameters","value":604339504832,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/stepfun-ai/Step-5-Preview"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"huggingface","metric":"hf_downloads_30d","value":105330,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"huggingface","metric":"hf_likes","value":566,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"huggingface","metric":"hf_trending","value":15,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"huggingface","metric":"hf_downloads_all_time","value":105330,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"huggingface","metric":"hf_parameters","value":310756322688,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"huggingface","metric":"hf_downloads_30d","value":103098,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"huggingface","metric":"hf_likes","value":750,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"huggingface","metric":"hf_trending","value":44,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"huggingface","metric":"hf_downloads_all_time","value":103098,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"huggingface","metric":"hf_parameters","value":1024216603392,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL"},{"modelId":"prism-ml/ternary-bonsai-2-27b","source":"huggingface","metric":"hf_downloads_30d","value":3268225,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/prism-ml/Ternary-Bonsai-2-27B-gguf"},{"modelId":"prism-ml/ternary-bonsai-2-27b","source":"huggingface","metric":"hf_likes","value":2758,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/prism-ml/Ternary-Bonsai-2-27B-gguf"},{"modelId":"prism-ml/ternary-bonsai-2-27b","source":"huggingface","metric":"hf_trending","value":77,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/prism-ml/Ternary-Bonsai-2-27B-gguf"},{"modelId":"prism-ml/ternary-bonsai-2-27b","source":"huggingface","metric":"hf_downloads_all_time","value":5121305,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/prism-ml/Ternary-Bonsai-2-27B-gguf"},{"modelId":"inclusionai/ling-3.0-flash-vl","source":"huggingface","metric":"hf_downloads_30d","value":14515,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/inclusionAI/Ling-3.0-flash-VL"},{"modelId":"inclusionai/ling-3.0-flash-vl","source":"huggingface","metric":"hf_likes","value":124,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/inclusionAI/Ling-3.0-flash-VL"},{"modelId":"inclusionai/ling-3.0-flash-vl","source":"huggingface","metric":"hf_trending","value":0,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/inclusionAI/Ling-3.0-flash-VL"},{"modelId":"inclusionai/ling-3.0-flash-vl","source":"huggingface","metric":"hf_downloads_all_time","value":22983,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/inclusionAI/Ling-3.0-flash-VL"},{"modelId":"inclusionai/ling-3.0-flash-vl","source":"huggingface","metric":"hf_parameters","value":124848460496,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/inclusionAI/Ling-3.0-flash-VL"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"huggingface","metric":"hf_downloads_30d","value":1367081,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"huggingface","metric":"hf_likes","value":4657,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"huggingface","metric":"hf_trending","value":169,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"huggingface","metric":"hf_downloads_all_time","value":1861562,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"huggingface","metric":"hf_parameters","value":763205315794,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"},{"modelId":"nex-agi/nex-n2.5-mini","source":"huggingface","metric":"hf_downloads_30d","value":3494,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/nex-agi/Nex-N2.5-mini"},{"modelId":"nex-agi/nex-n2.5-mini","source":"huggingface","metric":"hf_likes","value":871,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/nex-agi/Nex-N2.5-mini"},{"modelId":"nex-agi/nex-n2.5-mini","source":"huggingface","metric":"hf_trending","value":6,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/nex-agi/Nex-N2.5-mini"},{"modelId":"nex-agi/nex-n2.5-mini","source":"huggingface","metric":"hf_downloads_all_time","value":11850,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/nex-agi/Nex-N2.5-mini"},{"modelId":"nex-agi/nex-n2.5-mini","source":"huggingface","metric":"hf_parameters","value":35107181936,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/nex-agi/Nex-N2.5-mini"},{"modelId":"nex-agi/nex-n2.5-pro","source":"huggingface","metric":"hf_downloads_30d","value":2066,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/nex-agi/Nex-N2.5-Pro"},{"modelId":"nex-agi/nex-n2.5-pro","source":"huggingface","metric":"hf_likes","value":677,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/nex-agi/Nex-N2.5-Pro"},{"modelId":"nex-agi/nex-n2.5-pro","source":"huggingface","metric":"hf_trending","value":4,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/nex-agi/Nex-N2.5-Pro"},{"modelId":"nex-agi/nex-n2.5-pro","source":"huggingface","metric":"hf_downloads_all_time","value":33971,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/nex-agi/Nex-N2.5-Pro"},{"modelId":"nex-agi/nex-n2.5-pro","source":"huggingface","metric":"hf_parameters","value":396802360816,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/nex-agi/Nex-N2.5-Pro"},{"modelId":"ibm-granite/granite-4.2-8b","source":"huggingface","metric":"hf_downloads_30d","value":92215,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/ibm-granite/granite-4.2-8b"},{"modelId":"ibm-granite/granite-4.2-8b","source":"huggingface","metric":"hf_likes","value":105,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/ibm-granite/granite-4.2-8b"},{"modelId":"ibm-granite/granite-4.2-8b","source":"huggingface","metric":"hf_trending","value":6,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/ibm-granite/granite-4.2-8b"},{"modelId":"ibm-granite/granite-4.2-8b","source":"huggingface","metric":"hf_downloads_all_time","value":184299,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/ibm-granite/granite-4.2-8b"},{"modelId":"ibm-granite/granite-4.2-8b","source":"huggingface","metric":"hf_parameters","value":8791592960,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/ibm-granite/granite-4.2-8b"},{"modelId":"tencent/hy4-preview","source":"huggingface","metric":"hf_downloads_30d","value":21640,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/tencent/Hy4-preview"},{"modelId":"tencent/hy4-preview","source":"huggingface","metric":"hf_likes","value":509,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/tencent/Hy4-preview"},{"modelId":"tencent/hy4-preview","source":"huggingface","metric":"hf_trending","value":4,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/tencent/Hy4-preview"},{"modelId":"tencent/hy4-preview","source":"huggingface","metric":"hf_downloads_all_time","value":37928,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/tencent/Hy4-preview"},{"modelId":"tencent/hy4-preview","source":"huggingface","metric":"hf_parameters","value":779960992733,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/tencent/Hy4-preview"},{"modelId":"qwen/qwen3.8-flash","source":"huggingface","metric":"hf_downloads_30d","value":2494099,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-Flash-Next"},{"modelId":"qwen/qwen3.8-flash","source":"huggingface","metric":"hf_likes","value":6336,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-Flash-Next"},{"modelId":"qwen/qwen3.8-flash","source":"huggingface","metric":"hf_trending","value":171,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-Flash-Next"},{"modelId":"qwen/qwen3.8-flash","source":"huggingface","metric":"hf_downloads_all_time","value":3251164,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-Flash-Next"},{"modelId":"qwen/qwen3.8-flash","source":"huggingface","metric":"hf_parameters","value":179999981459,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-Flash-Next"},{"modelId":"z-ai/glm-5.3-flash","source":"huggingface","metric":"hf_downloads_30d","value":6536333,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-5.3-Flash"},{"modelId":"z-ai/glm-5.3-flash","source":"huggingface","metric":"hf_likes","value":2890,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-5.3-Flash"},{"modelId":"z-ai/glm-5.3-flash","source":"huggingface","metric":"hf_trending","value":55,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-5.3-Flash"},{"modelId":"z-ai/glm-5.3-flash","source":"huggingface","metric":"hf_downloads_all_time","value":9610922,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-5.3-Flash"},{"modelId":"z-ai/glm-5.3-flash","source":"huggingface","metric":"hf_parameters","value":321323031390,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-5.3-Flash"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"huggingface","metric":"hf_downloads_30d","value":476654,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"huggingface","metric":"hf_likes","value":955,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"huggingface","metric":"hf_trending","value":11,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"huggingface","metric":"hf_downloads_all_time","value":1242500,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp"},{"modelId":"deepseek/deepseek-v4-flash-vision-exp","source":"huggingface","metric":"hf_parameters","value":304646824126,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp"},{"modelId":"tencent/hy-mt2-1.8b","source":"huggingface","metric":"hf_downloads_30d","value":27017,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/tencent/Hy-MT2-1.8B"},{"modelId":"tencent/hy-mt2-1.8b","source":"huggingface","metric":"hf_likes","value":1259,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/tencent/Hy-MT2-1.8B"},{"modelId":"tencent/hy-mt2-1.8b","source":"huggingface","metric":"hf_trending","value":6,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/tencent/Hy-MT2-1.8B"},{"modelId":"tencent/hy-mt2-1.8b","source":"huggingface","metric":"hf_downloads_all_time","value":280222,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/tencent/Hy-MT2-1.8B"},{"modelId":"tencent/hy-mt2-1.8b","source":"huggingface","metric":"hf_parameters","value":2038515712,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/tencent/Hy-MT2-1.8B"},{"modelId":"tencent/hy-mt2-30b-a3b","source":"huggingface","metric":"hf_downloads_30d","value":2983,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/tencent/Hy-MT2-30B-A3B"},{"modelId":"tencent/hy-mt2-30b-a3b","source":"huggingface","metric":"hf_likes","value":509,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/tencent/Hy-MT2-30B-A3B"},{"modelId":"tencent/hy-mt2-30b-a3b","source":"huggingface","metric":"hf_trending","value":2,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/tencent/Hy-MT2-30B-A3B"},{"modelId":"tencent/hy-mt2-30b-a3b","source":"huggingface","metric":"hf_downloads_all_time","value":237443,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/tencent/Hy-MT2-30B-A3B"},{"modelId":"tencent/hy-mt2-30b-a3b","source":"huggingface","metric":"hf_parameters","value":30064725888,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/tencent/Hy-MT2-30B-A3B"},{"modelId":"tencent/hy-mt2-7b","source":"huggingface","metric":"hf_downloads_30d","value":11514,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/tencent/Hy-MT2-7B"},{"modelId":"tencent/hy-mt2-7b","source":"huggingface","metric":"hf_likes","value":213,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/tencent/Hy-MT2-7B"},{"modelId":"tencent/hy-mt2-7b","source":"huggingface","metric":"hf_trending","value":1,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/tencent/Hy-MT2-7B"},{"modelId":"tencent/hy-mt2-7b","source":"huggingface","metric":"hf_downloads_all_time","value":108672,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/tencent/Hy-MT2-7B"},{"modelId":"tencent/hy-mt2-7b","source":"huggingface","metric":"hf_parameters","value":8029540352,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/tencent/Hy-MT2-7B"},{"modelId":"z-ai/glm-5.3","source":"huggingface","metric":"hf_downloads_30d","value":1846414,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-5.3"},{"modelId":"z-ai/glm-5.3","source":"huggingface","metric":"hf_likes","value":2264,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-5.3"},{"modelId":"z-ai/glm-5.3","source":"huggingface","metric":"hf_trending","value":58,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-5.3"},{"modelId":"z-ai/glm-5.3","source":"huggingface","metric":"hf_downloads_all_time","value":2815034,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-5.3"},{"modelId":"z-ai/glm-5.3","source":"huggingface","metric":"hf_parameters","value":753329940480,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-5.3"},{"modelId":"qwen/qwen3.8-27b","source":"huggingface","metric":"hf_downloads_30d","value":7458401,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-27B"},{"modelId":"qwen/qwen3.8-27b","source":"huggingface","metric":"hf_likes","value":18016,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-27B"},{"modelId":"qwen/qwen3.8-27b","source":"huggingface","metric":"hf_trending","value":287,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-27B"},{"modelId":"qwen/qwen3.8-27b","source":"huggingface","metric":"hf_downloads_all_time","value":16821657,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-27B"},{"modelId":"qwen/qwen3.8-27b","source":"huggingface","metric":"hf_parameters","value":27781427952,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-27B"},{"modelId":"qwen/qwen3.8-2.4t-a95b","source":"huggingface","metric":"hf_downloads_30d","value":25658,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B"},{"modelId":"qwen/qwen3.8-2.4t-a95b","source":"huggingface","metric":"hf_likes","value":1321,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B"},{"modelId":"qwen/qwen3.8-2.4t-a95b","source":"huggingface","metric":"hf_trending","value":10,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B"},{"modelId":"qwen/qwen3.8-2.4t-a95b","source":"huggingface","metric":"hf_downloads_all_time","value":98067,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B"},{"modelId":"qwen/qwen3.8-2.4t-a95b","source":"huggingface","metric":"hf_parameters","value":2446182725504,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"huggingface","metric":"hf_downloads_30d","value":154886,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"huggingface","metric":"hf_likes","value":898,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"huggingface","metric":"hf_trending","value":3,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"huggingface","metric":"hf_downloads_all_time","value":368730,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"huggingface","metric":"hf_parameters","value":1650497936906,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"huggingface","metric":"hf_downloads_30d","value":688412,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"huggingface","metric":"hf_likes","value":241,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"huggingface","metric":"hf_trending","value":8,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"huggingface","metric":"hf_downloads_all_time","value":1385747,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"huggingface","metric":"hf_parameters","value":31577937344,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16"},{"modelId":"meta/muse-glimmer-30b","source":"huggingface","metric":"hf_downloads_30d","value":234792,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-models/Muse-Glimmer-30B"},{"modelId":"meta/muse-glimmer-30b","source":"huggingface","metric":"hf_likes","value":2060,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-models/Muse-Glimmer-30B"},{"modelId":"meta/muse-glimmer-30b","source":"huggingface","metric":"hf_trending","value":38,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-models/Muse-Glimmer-30B"},{"modelId":"meta/muse-glimmer-30b","source":"huggingface","metric":"hf_downloads_all_time","value":1031839,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-models/Muse-Glimmer-30B"},{"modelId":"meta/muse-glimmer-30b","source":"huggingface","metric":"hf_parameters","value":29776626688,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-models/Muse-Glimmer-30B"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"huggingface","metric":"hf_downloads_30d","value":4328385,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"huggingface","metric":"hf_likes","value":4083,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"huggingface","metric":"hf_downloads_all_time","value":11364010,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"huggingface","metric":"hf_parameters","value":304180418494,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731"},{"modelId":"thinkingmachines/inkling-small","source":"huggingface","metric":"hf_downloads_30d","value":777414,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/thinkingmachines/Inkling-Small"},{"modelId":"thinkingmachines/inkling-small","source":"huggingface","metric":"hf_likes","value":422,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/thinkingmachines/Inkling-Small"},{"modelId":"thinkingmachines/inkling-small","source":"huggingface","metric":"hf_trending","value":3,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/thinkingmachines/Inkling-Small"},{"modelId":"thinkingmachines/inkling-small","source":"huggingface","metric":"hf_downloads_all_time","value":1387823,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/thinkingmachines/Inkling-Small"},{"modelId":"thinkingmachines/inkling-small","source":"huggingface","metric":"hf_parameters","value":265956439090,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/thinkingmachines/Inkling-Small"},{"modelId":"inclusionai/ling-3.0-flash","source":"huggingface","metric":"hf_downloads_30d","value":10287,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/inclusionAI/Ling-3.0-flash"},{"modelId":"inclusionai/ling-3.0-flash","source":"huggingface","metric":"hf_likes","value":433,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/inclusionAI/Ling-3.0-flash"},{"modelId":"inclusionai/ling-3.0-flash","source":"huggingface","metric":"hf_trending","value":3,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/inclusionAI/Ling-3.0-flash"},{"modelId":"inclusionai/ling-3.0-flash","source":"huggingface","metric":"hf_downloads_all_time","value":43185,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/inclusionAI/Ling-3.0-flash"},{"modelId":"inclusionai/ling-3.0-flash","source":"huggingface","metric":"hf_parameters","value":127486405600,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/inclusionAI/Ling-3.0-flash"},{"modelId":"poolside/laguna-s-2.1","source":"huggingface","metric":"hf_downloads_30d","value":356956,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/poolside/Laguna-S-2.1"},{"modelId":"poolside/laguna-s-2.1","source":"huggingface","metric":"hf_likes","value":1056,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/poolside/Laguna-S-2.1"},{"modelId":"poolside/laguna-s-2.1","source":"huggingface","metric":"hf_downloads_all_time","value":505257,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/poolside/Laguna-S-2.1"},{"modelId":"poolside/laguna-s-2.1","source":"huggingface","metric":"hf_parameters","value":117561977600,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/poolside/Laguna-S-2.1"},{"modelId":"meituan/longcat-2.0","source":"huggingface","metric":"hf_downloads_30d","value":2280,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meituan-longcat/LongCat-2.0"},{"modelId":"meituan/longcat-2.0","source":"huggingface","metric":"hf_likes","value":282,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meituan-longcat/LongCat-2.0"},{"modelId":"meituan/longcat-2.0","source":"huggingface","metric":"hf_trending","value":1,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meituan-longcat/LongCat-2.0"},{"modelId":"meituan/longcat-2.0","source":"huggingface","metric":"hf_downloads_all_time","value":8258,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meituan-longcat/LongCat-2.0"},{"modelId":"meituan/longcat-2.0","source":"huggingface","metric":"hf_parameters","value":1775560491136,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meituan-longcat/LongCat-2.0"},{"modelId":"thinkingmachines/inkling","source":"huggingface","metric":"hf_downloads_30d","value":1311894,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/thinkingmachines/Inkling"},{"modelId":"thinkingmachines/inkling","source":"huggingface","metric":"hf_likes","value":1819,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/thinkingmachines/Inkling"},{"modelId":"thinkingmachines/inkling","source":"huggingface","metric":"hf_trending","value":6,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/thinkingmachines/Inkling"},{"modelId":"thinkingmachines/inkling","source":"huggingface","metric":"hf_downloads_all_time","value":1827337,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/thinkingmachines/Inkling"},{"modelId":"thinkingmachines/inkling","source":"huggingface","metric":"hf_parameters","value":952377623626,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/thinkingmachines/Inkling"},{"modelId":"moonshotai/kimi-k3","source":"huggingface","metric":"hf_downloads_30d","value":1012867,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3"},{"modelId":"moonshotai/kimi-k3","source":"huggingface","metric":"hf_likes","value":11775,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3"},{"modelId":"moonshotai/kimi-k3","source":"huggingface","metric":"hf_trending","value":49,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3"},{"modelId":"moonshotai/kimi-k3","source":"huggingface","metric":"hf_downloads_all_time","value":5614344,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3"},{"modelId":"moonshotai/kimi-k3","source":"huggingface","metric":"hf_parameters","value":2779931837184,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3"},{"modelId":"tencent/hy3","source":"huggingface","metric":"hf_downloads_30d","value":725109,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/tencent/Hy3"},{"modelId":"tencent/hy3","source":"huggingface","metric":"hf_likes","value":983,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/tencent/Hy3"},{"modelId":"tencent/hy3","source":"huggingface","metric":"hf_trending","value":2,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/tencent/Hy3"},{"modelId":"tencent/hy3","source":"huggingface","metric":"hf_downloads_all_time","value":767401,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/tencent/Hy3"},{"modelId":"tencent/hy3","source":"huggingface","metric":"hf_parameters","value":298786155776,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/tencent/Hy3"},{"modelId":"poolside/laguna-xs-2.1","source":"huggingface","metric":"hf_downloads_30d","value":434630,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/poolside/Laguna-XS-2.1"},{"modelId":"poolside/laguna-xs-2.1","source":"huggingface","metric":"hf_likes","value":257,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/poolside/Laguna-XS-2.1"},{"modelId":"poolside/laguna-xs-2.1","source":"huggingface","metric":"hf_trending","value":1,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/poolside/Laguna-XS-2.1"},{"modelId":"poolside/laguna-xs-2.1","source":"huggingface","metric":"hf_downloads_all_time","value":539466,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/poolside/Laguna-XS-2.1"},{"modelId":"poolside/laguna-xs-2.1","source":"huggingface","metric":"hf_parameters","value":33442617088,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/poolside/Laguna-XS-2.1"},{"modelId":"z-ai/glm-5.2","source":"huggingface","metric":"hf_downloads_30d","value":411387,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-5.2"},{"modelId":"z-ai/glm-5.2","source":"huggingface","metric":"hf_likes","value":5179,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-5.2"},{"modelId":"z-ai/glm-5.2","source":"huggingface","metric":"hf_trending","value":5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-5.2"},{"modelId":"z-ai/glm-5.2","source":"huggingface","metric":"hf_downloads_all_time","value":4818310,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-5.2"},{"modelId":"z-ai/glm-5.2","source":"huggingface","metric":"hf_parameters","value":753329940480,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-5.2"},{"modelId":"moonshotai/kimi-k2.7-code","source":"huggingface","metric":"hf_downloads_30d","value":107995,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.7-Code"},{"modelId":"moonshotai/kimi-k2.7-code","source":"huggingface","metric":"hf_likes","value":1421,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.7-Code"},{"modelId":"moonshotai/kimi-k2.7-code","source":"huggingface","metric":"hf_trending","value":4,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.7-Code"},{"modelId":"moonshotai/kimi-k2.7-code","source":"huggingface","metric":"hf_downloads_all_time","value":1950083,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.7-Code"},{"modelId":"moonshotai/kimi-k2.7-code","source":"huggingface","metric":"hf_parameters","value":1026879376368,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.7-Code"},{"modelId":"nvidia/nemotron-3.5-content-safety","source":"huggingface","metric":"hf_downloads_30d","value":26418,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/nvidia/Nemotron-3.5-Content-Safety"},{"modelId":"nvidia/nemotron-3.5-content-safety","source":"huggingface","metric":"hf_likes","value":63,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/nvidia/Nemotron-3.5-Content-Safety"},{"modelId":"nvidia/nemotron-3.5-content-safety","source":"huggingface","metric":"hf_trending","value":3,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/nvidia/Nemotron-3.5-Content-Safety"},{"modelId":"nvidia/nemotron-3.5-content-safety","source":"huggingface","metric":"hf_downloads_all_time","value":338771,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/nvidia/Nemotron-3.5-Content-Safety"},{"modelId":"nvidia/nemotron-3.5-content-safety","source":"huggingface","metric":"hf_parameters","value":4300079472,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/nvidia/Nemotron-3.5-Content-Safety"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"huggingface","metric":"hf_downloads_30d","value":992685,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"huggingface","metric":"hf_likes","value":367,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"huggingface","metric":"hf_downloads_all_time","value":1994681,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"huggingface","metric":"hf_parameters","value":560524578816,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16"},{"modelId":"minimax/minimax-m3","source":"huggingface","metric":"hf_downloads_30d","value":194147,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3"},{"modelId":"minimax/minimax-m3","source":"huggingface","metric":"hf_likes","value":1585,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3"},{"modelId":"minimax/minimax-m3","source":"huggingface","metric":"hf_trending","value":8,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3"},{"modelId":"minimax/minimax-m3","source":"huggingface","metric":"hf_downloads_all_time","value":891764,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3"},{"modelId":"minimax/minimax-m3","source":"huggingface","metric":"hf_parameters","value":427040140160,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3"},{"modelId":"stepfun/step-3.7-flash","source":"huggingface","metric":"hf_downloads_30d","value":18761,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/stepfun-ai/Step-3.7-Flash"},{"modelId":"stepfun/step-3.7-flash","source":"huggingface","metric":"hf_likes","value":462,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/stepfun-ai/Step-3.7-Flash"},{"modelId":"stepfun/step-3.7-flash","source":"huggingface","metric":"hf_trending","value":1,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/stepfun-ai/Step-3.7-Flash"},{"modelId":"stepfun/step-3.7-flash","source":"huggingface","metric":"hf_downloads_all_time","value":404548,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/stepfun-ai/Step-3.7-Flash"},{"modelId":"stepfun/step-3.7-flash","source":"huggingface","metric":"hf_parameters","value":201365316160,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/stepfun-ai/Step-3.7-Flash"},{"modelId":"qwen/qwen3.6-35b-a3b","source":"huggingface","metric":"hf_downloads_30d","value":3654945,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B"},{"modelId":"qwen/qwen3.6-35b-a3b","source":"huggingface","metric":"hf_likes","value":3010,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B"},{"modelId":"qwen/qwen3.6-35b-a3b","source":"huggingface","metric":"hf_trending","value":29,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B"},{"modelId":"qwen/qwen3.6-35b-a3b","source":"huggingface","metric":"hf_downloads_all_time","value":31877620,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B"},{"modelId":"qwen/qwen3.6-35b-a3b","source":"huggingface","metric":"hf_parameters","value":35951822704,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B"},{"modelId":"qwen/qwen3.6-27b","source":"huggingface","metric":"hf_downloads_30d","value":2310377,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-27B"},{"modelId":"qwen/qwen3.6-27b","source":"huggingface","metric":"hf_likes","value":2331,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-27B"},{"modelId":"qwen/qwen3.6-27b","source":"huggingface","metric":"hf_trending","value":4,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-27B"},{"modelId":"qwen/qwen3.6-27b","source":"huggingface","metric":"hf_downloads_all_time","value":29098878,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-27B"},{"modelId":"qwen/qwen3.6-27b","source":"huggingface","metric":"hf_parameters","value":27781427952,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.6-27B"},{"modelId":"deepseek/deepseek-v4-pro","source":"huggingface","metric":"hf_downloads_30d","value":364869,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro"},{"modelId":"deepseek/deepseek-v4-pro","source":"huggingface","metric":"hf_likes","value":5666,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro"},{"modelId":"deepseek/deepseek-v4-pro","source":"huggingface","metric":"hf_trending","value":17,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro"},{"modelId":"deepseek/deepseek-v4-pro","source":"huggingface","metric":"hf_downloads_all_time","value":10917488,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro"},{"modelId":"deepseek/deepseek-v4-pro","source":"huggingface","metric":"hf_parameters","value":1598839674782,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro"},{"modelId":"deepseek/deepseek-v4-flash","source":"huggingface","metric":"hf_downloads_30d","value":798572,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash"},{"modelId":"deepseek/deepseek-v4-flash","source":"huggingface","metric":"hf_likes","value":2326,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash"},{"modelId":"deepseek/deepseek-v4-flash","source":"huggingface","metric":"hf_trending","value":6,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash"},{"modelId":"deepseek/deepseek-v4-flash","source":"huggingface","metric":"hf_downloads_all_time","value":12795357,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash"},{"modelId":"deepseek/deepseek-v4-flash","source":"huggingface","metric":"hf_parameters","value":290944616402,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash"},{"modelId":"tencent/hy3-preview","source":"huggingface","metric":"hf_downloads_30d","value":91614,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/tencent/Hy3-preview"},{"modelId":"tencent/hy3-preview","source":"huggingface","metric":"hf_likes","value":313,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/tencent/Hy3-preview"},{"modelId":"tencent/hy3-preview","source":"huggingface","metric":"hf_trending","value":1,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/tencent/Hy3-preview"},{"modelId":"tencent/hy3-preview","source":"huggingface","metric":"hf_downloads_all_time","value":483831,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/tencent/Hy3-preview"},{"modelId":"tencent/hy3-preview","source":"huggingface","metric":"hf_parameters","value":298786155776,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/tencent/Hy3-preview"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"huggingface","metric":"hf_downloads_30d","value":17588,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"huggingface","metric":"hf_likes","value":766,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"huggingface","metric":"hf_trending","value":2,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"huggingface","metric":"hf_downloads_all_time","value":349105,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"huggingface","metric":"hf_parameters","value":1023182841600,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro"},{"modelId":"xiaomi/mimo-v2.5","source":"huggingface","metric":"hf_downloads_30d","value":152779,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5"},{"modelId":"xiaomi/mimo-v2.5","source":"huggingface","metric":"hf_likes","value":431,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5"},{"modelId":"xiaomi/mimo-v2.5","source":"huggingface","metric":"hf_trending","value":0,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5"},{"modelId":"xiaomi/mimo-v2.5","source":"huggingface","metric":"hf_downloads_all_time","value":1587437,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5"},{"modelId":"xiaomi/mimo-v2.5","source":"huggingface","metric":"hf_parameters","value":310775040000,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5"},{"modelId":"moonshotai/kimi-k2.6","source":"huggingface","metric":"hf_downloads_30d","value":371009,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6"},{"modelId":"moonshotai/kimi-k2.6","source":"huggingface","metric":"hf_likes","value":1633,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6"},{"modelId":"moonshotai/kimi-k2.6","source":"huggingface","metric":"hf_trending","value":8,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6"},{"modelId":"moonshotai/kimi-k2.6","source":"huggingface","metric":"hf_downloads_all_time","value":8570492,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6"},{"modelId":"moonshotai/kimi-k2.6","source":"huggingface","metric":"hf_parameters","value":1026879376368,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6"},{"modelId":"z-ai/glm-5.1","source":"huggingface","metric":"hf_downloads_30d","value":547020,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-5.1"},{"modelId":"z-ai/glm-5.1","source":"huggingface","metric":"hf_likes","value":1846,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-5.1"},{"modelId":"z-ai/glm-5.1","source":"huggingface","metric":"hf_trending","value":1,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-5.1"},{"modelId":"z-ai/glm-5.1","source":"huggingface","metric":"hf_downloads_all_time","value":1305928,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-5.1"},{"modelId":"z-ai/glm-5.1","source":"huggingface","metric":"hf_parameters","value":753864139008,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-5.1"},{"modelId":"google/gemma-4-26b-a4b-it","source":"huggingface","metric":"hf_downloads_30d","value":10291857,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/google/gemma-4-26B-A4B-it"},{"modelId":"google/gemma-4-26b-a4b-it","source":"huggingface","metric":"hf_likes","value":1679,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/google/gemma-4-26B-A4B-it"},{"modelId":"google/gemma-4-26b-a4b-it","source":"huggingface","metric":"hf_trending","value":29,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/google/gemma-4-26B-A4B-it"},{"modelId":"google/gemma-4-26b-a4b-it","source":"huggingface","metric":"hf_downloads_all_time","value":71810157,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/google/gemma-4-26B-A4B-it"},{"modelId":"google/gemma-4-26b-a4b-it","source":"huggingface","metric":"hf_parameters","value":25805936206,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/google/gemma-4-26B-A4B-it"},{"modelId":"google/gemma-4-31b-it","source":"huggingface","metric":"hf_downloads_30d","value":8974781,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/google/gemma-4-31B-it"},{"modelId":"google/gemma-4-31b-it","source":"huggingface","metric":"hf_likes","value":4160,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/google/gemma-4-31B-it"},{"modelId":"google/gemma-4-31b-it","source":"huggingface","metric":"hf_trending","value":39,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/google/gemma-4-31B-it"},{"modelId":"google/gemma-4-31b-it","source":"huggingface","metric":"hf_downloads_all_time","value":68430888,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/google/gemma-4-31B-it"},{"modelId":"google/gemma-4-31b-it","source":"huggingface","metric":"hf_parameters","value":31273088876,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/google/gemma-4-31B-it"},{"modelId":"arcee-ai/trinity-large-thinking","source":"huggingface","metric":"hf_downloads_30d","value":2250,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/arcee-ai/Trinity-Large-Thinking"},{"modelId":"arcee-ai/trinity-large-thinking","source":"huggingface","metric":"hf_likes","value":190,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/arcee-ai/Trinity-Large-Thinking"},{"modelId":"arcee-ai/trinity-large-thinking","source":"huggingface","metric":"hf_trending","value":0,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/arcee-ai/Trinity-Large-Thinking"},{"modelId":"arcee-ai/trinity-large-thinking","source":"huggingface","metric":"hf_downloads_all_time","value":72066,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/arcee-ai/Trinity-Large-Thinking"},{"modelId":"arcee-ai/trinity-large-thinking","source":"huggingface","metric":"hf_parameters","value":398635286016,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/arcee-ai/Trinity-Large-Thinking"},{"modelId":"rekaai/reka-edge","source":"huggingface","metric":"hf_downloads_30d","value":751,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/RekaAI/reka-edge-2603"},{"modelId":"rekaai/reka-edge","source":"huggingface","metric":"hf_likes","value":134,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/RekaAI/reka-edge-2603"},{"modelId":"rekaai/reka-edge","source":"huggingface","metric":"hf_trending","value":1,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/RekaAI/reka-edge-2603"},{"modelId":"rekaai/reka-edge","source":"huggingface","metric":"hf_downloads_all_time","value":17365,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/RekaAI/reka-edge-2603"},{"modelId":"rekaai/reka-edge","source":"huggingface","metric":"hf_parameters","value":7128509568,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/RekaAI/reka-edge-2603"},{"modelId":"minimax/minimax-m2.7","source":"huggingface","metric":"hf_downloads_30d","value":535418,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2.7"},{"modelId":"minimax/minimax-m2.7","source":"huggingface","metric":"hf_likes","value":1256,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2.7"},{"modelId":"minimax/minimax-m2.7","source":"huggingface","metric":"hf_trending","value":1,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2.7"},{"modelId":"minimax/minimax-m2.7","source":"huggingface","metric":"hf_downloads_all_time","value":7889186,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2.7"},{"modelId":"minimax/minimax-m2.7","source":"huggingface","metric":"hf_parameters","value":228689764864,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2.7"},{"modelId":"mistralai/mistral-small-2603","source":"huggingface","metric":"hf_downloads_30d","value":71588,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Mistral-Small-4-119B-2603"},{"modelId":"mistralai/mistral-small-2603","source":"huggingface","metric":"hf_likes","value":454,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Mistral-Small-4-119B-2603"},{"modelId":"mistralai/mistral-small-2603","source":"huggingface","metric":"hf_trending","value":6,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Mistral-Small-4-119B-2603"},{"modelId":"mistralai/mistral-small-2603","source":"huggingface","metric":"hf_downloads_all_time","value":696030,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Mistral-Small-4-119B-2603"},{"modelId":"mistralai/mistral-small-2603","source":"huggingface","metric":"hf_parameters","value":119401317952,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Mistral-Small-4-119B-2603"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"huggingface","metric":"hf_downloads_30d","value":62674,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"huggingface","metric":"hf_likes","value":291,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"huggingface","metric":"hf_trending","value":2,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"huggingface","metric":"hf_downloads_all_time","value":2659126,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"huggingface","metric":"hf_parameters","value":123611012096,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8"},{"modelId":"qwen/qwen3.5-9b","source":"huggingface","metric":"hf_downloads_30d","value":7483178,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-9B"},{"modelId":"qwen/qwen3.5-9b","source":"huggingface","metric":"hf_likes","value":2206,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-9B"},{"modelId":"qwen/qwen3.5-9b","source":"huggingface","metric":"hf_trending","value":32,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-9B"},{"modelId":"qwen/qwen3.5-9b","source":"huggingface","metric":"hf_downloads_all_time","value":70742857,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-9B"},{"modelId":"qwen/qwen3.5-9b","source":"huggingface","metric":"hf_parameters","value":9653104368,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-9B"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"huggingface","metric":"hf_downloads_30d","value":1393154,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-35B-A3B"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"huggingface","metric":"hf_likes","value":1538,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-35B-A3B"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"huggingface","metric":"hf_trending","value":6,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-35B-A3B"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"huggingface","metric":"hf_downloads_all_time","value":20653434,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-35B-A3B"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"huggingface","metric":"hf_parameters","value":35951822704,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-35B-A3B"},{"modelId":"qwen/qwen3.5-27b","source":"huggingface","metric":"hf_downloads_30d","value":1763739,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-27B"},{"modelId":"qwen/qwen3.5-27b","source":"huggingface","metric":"hf_likes","value":1069,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-27B"},{"modelId":"qwen/qwen3.5-27b","source":"huggingface","metric":"hf_trending","value":5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-27B"},{"modelId":"qwen/qwen3.5-27b","source":"huggingface","metric":"hf_downloads_all_time","value":21067972,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-27B"},{"modelId":"qwen/qwen3.5-27b","source":"huggingface","metric":"hf_parameters","value":27781427952,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-27B"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"huggingface","metric":"hf_downloads_30d","value":696355,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-122B-A10B"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"huggingface","metric":"hf_likes","value":639,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-122B-A10B"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"huggingface","metric":"hf_downloads_all_time","value":7680234,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-122B-A10B"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"huggingface","metric":"hf_parameters","value":125086497008,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-122B-A10B"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"huggingface","metric":"hf_downloads_30d","value":600545,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-397B-A17B"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"huggingface","metric":"hf_likes","value":1577,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-397B-A17B"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"huggingface","metric":"hf_trending","value":4,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-397B-A17B"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"huggingface","metric":"hf_downloads_all_time","value":5975189,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-397B-A17B"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"huggingface","metric":"hf_parameters","value":403397928944,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3.5-397B-A17B"},{"modelId":"minimax/minimax-m2.5","source":"huggingface","metric":"hf_downloads_30d","value":782757,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2.5"},{"modelId":"minimax/minimax-m2.5","source":"huggingface","metric":"hf_likes","value":1521,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2.5"},{"modelId":"minimax/minimax-m2.5","source":"huggingface","metric":"hf_downloads_all_time","value":5715333,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2.5"},{"modelId":"minimax/minimax-m2.5","source":"huggingface","metric":"hf_parameters","value":228703644928,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2.5"},{"modelId":"z-ai/glm-5","source":"huggingface","metric":"hf_downloads_30d","value":896896,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-5"},{"modelId":"z-ai/glm-5","source":"huggingface","metric":"hf_likes","value":2138,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-5"},{"modelId":"z-ai/glm-5","source":"huggingface","metric":"hf_trending","value":1,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-5"},{"modelId":"z-ai/glm-5","source":"huggingface","metric":"hf_downloads_all_time","value":2255385,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-5"},{"modelId":"z-ai/glm-5","source":"huggingface","metric":"hf_parameters","value":753864139008,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-5"},{"modelId":"qwen/qwen3-coder-next","source":"huggingface","metric":"hf_downloads_30d","value":518843,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-Coder-Next"},{"modelId":"qwen/qwen3-coder-next","source":"huggingface","metric":"hf_likes","value":1702,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-Coder-Next"},{"modelId":"qwen/qwen3-coder-next","source":"huggingface","metric":"hf_trending","value":6,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-Coder-Next"},{"modelId":"qwen/qwen3-coder-next","source":"huggingface","metric":"hf_downloads_all_time","value":7271755,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-Coder-Next"},{"modelId":"qwen/qwen3-coder-next","source":"huggingface","metric":"hf_parameters","value":79674391296,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-Coder-Next"},{"modelId":"stepfun/step-3.5-flash","source":"huggingface","metric":"hf_downloads_30d","value":259435,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/stepfun-ai/Step-3.5-Flash"},{"modelId":"stepfun/step-3.5-flash","source":"huggingface","metric":"hf_likes","value":840,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/stepfun-ai/Step-3.5-Flash"},{"modelId":"stepfun/step-3.5-flash","source":"huggingface","metric":"hf_trending","value":1,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/stepfun-ai/Step-3.5-Flash"},{"modelId":"stepfun/step-3.5-flash","source":"huggingface","metric":"hf_downloads_all_time","value":1835165,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/stepfun-ai/Step-3.5-Flash"},{"modelId":"stepfun/step-3.5-flash","source":"huggingface","metric":"hf_parameters","value":199384301376,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/stepfun-ai/Step-3.5-Flash"},{"modelId":"moonshotai/kimi-k2.5","source":"huggingface","metric":"hf_downloads_30d","value":320291,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.5"},{"modelId":"moonshotai/kimi-k2.5","source":"huggingface","metric":"hf_likes","value":2890,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.5"},{"modelId":"moonshotai/kimi-k2.5","source":"huggingface","metric":"hf_trending","value":6,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.5"},{"modelId":"moonshotai/kimi-k2.5","source":"huggingface","metric":"hf_downloads_all_time","value":16143810,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.5"},{"modelId":"moonshotai/kimi-k2.5","source":"huggingface","metric":"hf_parameters","value":1026879376368,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.5"},{"modelId":"z-ai/glm-4.7-flash","source":"huggingface","metric":"hf_downloads_30d","value":1125508,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-4.7-Flash"},{"modelId":"z-ai/glm-4.7-flash","source":"huggingface","metric":"hf_likes","value":1879,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-4.7-Flash"},{"modelId":"z-ai/glm-4.7-flash","source":"huggingface","metric":"hf_trending","value":4,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-4.7-Flash"},{"modelId":"z-ai/glm-4.7-flash","source":"huggingface","metric":"hf_downloads_all_time","value":14814399,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-4.7-Flash"},{"modelId":"z-ai/glm-4.7-flash","source":"huggingface","metric":"hf_parameters","value":31221488576,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-4.7-Flash"},{"modelId":"minimax/minimax-m2.1","source":"huggingface","metric":"hf_downloads_30d","value":10693,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2.1"},{"modelId":"minimax/minimax-m2.1","source":"huggingface","metric":"hf_likes","value":1370,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2.1"},{"modelId":"minimax/minimax-m2.1","source":"huggingface","metric":"hf_trending","value":3,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2.1"},{"modelId":"minimax/minimax-m2.1","source":"huggingface","metric":"hf_downloads_all_time","value":502697,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2.1"},{"modelId":"minimax/minimax-m2.1","source":"huggingface","metric":"hf_parameters","value":228689764864,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2.1"},{"modelId":"z-ai/glm-4.7","source":"huggingface","metric":"hf_downloads_30d","value":82803,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-4.7"},{"modelId":"z-ai/glm-4.7","source":"huggingface","metric":"hf_likes","value":2068,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-4.7"},{"modelId":"z-ai/glm-4.7","source":"huggingface","metric":"hf_downloads_all_time","value":902738,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-4.7"},{"modelId":"z-ai/glm-4.7","source":"huggingface","metric":"hf_parameters","value":358337791296,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-4.7"},{"modelId":"nvidia/nemotron-3-nano-30b-a3b","source":"huggingface","metric":"hf_downloads_30d","value":1189428,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16"},{"modelId":"nvidia/nemotron-3-nano-30b-a3b","source":"huggingface","metric":"hf_likes","value":831,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16"},{"modelId":"nvidia/nemotron-3-nano-30b-a3b","source":"huggingface","metric":"hf_trending","value":2,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16"},{"modelId":"nvidia/nemotron-3-nano-30b-a3b","source":"huggingface","metric":"hf_downloads_all_time","value":10716774,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16"},{"modelId":"nvidia/nemotron-3-nano-30b-a3b","source":"huggingface","metric":"hf_parameters","value":31577937344,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16"},{"modelId":"mistralai/devstral-2512","source":"huggingface","metric":"hf_downloads_30d","value":5281,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Devstral-2-123B-Instruct-2512"},{"modelId":"mistralai/devstral-2512","source":"huggingface","metric":"hf_likes","value":353,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Devstral-2-123B-Instruct-2512"},{"modelId":"mistralai/devstral-2512","source":"huggingface","metric":"hf_trending","value":3,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Devstral-2-123B-Instruct-2512"},{"modelId":"mistralai/devstral-2512","source":"huggingface","metric":"hf_downloads_all_time","value":352845,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Devstral-2-123B-Instruct-2512"},{"modelId":"mistralai/devstral-2512","source":"huggingface","metric":"hf_parameters","value":125025989840,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Devstral-2-123B-Instruct-2512"},{"modelId":"z-ai/glm-4.6v","source":"huggingface","metric":"hf_downloads_30d","value":3546,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-4.6V"},{"modelId":"z-ai/glm-4.6v","source":"huggingface","metric":"hf_likes","value":398,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-4.6V"},{"modelId":"z-ai/glm-4.6v","source":"huggingface","metric":"hf_trending","value":1,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-4.6V"},{"modelId":"z-ai/glm-4.6v","source":"huggingface","metric":"hf_downloads_all_time","value":435601,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-4.6V"},{"modelId":"z-ai/glm-4.6v","source":"huggingface","metric":"hf_parameters","value":107710933120,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-4.6V"},{"modelId":"mistralai/ministral-14b-2512","source":"huggingface","metric":"hf_downloads_30d","value":121665,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Ministral-3-14B-Instruct-2512"},{"modelId":"mistralai/ministral-14b-2512","source":"huggingface","metric":"hf_likes","value":344,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Ministral-3-14B-Instruct-2512"},{"modelId":"mistralai/ministral-14b-2512","source":"huggingface","metric":"hf_downloads_all_time","value":2392459,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Ministral-3-14B-Instruct-2512"},{"modelId":"mistralai/ministral-14b-2512","source":"huggingface","metric":"hf_parameters","value":13945032240,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Ministral-3-14B-Instruct-2512"},{"modelId":"mistralai/ministral-8b-2512","source":"huggingface","metric":"hf_downloads_30d","value":119896,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Ministral-3-8B-Instruct-2512"},{"modelId":"mistralai/ministral-8b-2512","source":"huggingface","metric":"hf_likes","value":228,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Ministral-3-8B-Instruct-2512"},{"modelId":"mistralai/ministral-8b-2512","source":"huggingface","metric":"hf_trending","value":7,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Ministral-3-8B-Instruct-2512"},{"modelId":"mistralai/ministral-8b-2512","source":"huggingface","metric":"hf_downloads_all_time","value":1236741,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Ministral-3-8B-Instruct-2512"},{"modelId":"mistralai/ministral-8b-2512","source":"huggingface","metric":"hf_parameters","value":8918026716,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Ministral-3-8B-Instruct-2512"},{"modelId":"mistralai/ministral-3b-2512","source":"huggingface","metric":"hf_downloads_30d","value":100787,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Ministral-3-3B-Instruct-2512"},{"modelId":"mistralai/ministral-3b-2512","source":"huggingface","metric":"hf_likes","value":308,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Ministral-3-3B-Instruct-2512"},{"modelId":"mistralai/ministral-3b-2512","source":"huggingface","metric":"hf_downloads_all_time","value":3962799,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Ministral-3-3B-Instruct-2512"},{"modelId":"mistralai/ministral-3b-2512","source":"huggingface","metric":"hf_parameters","value":3849090048,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Ministral-3-3B-Instruct-2512"},{"modelId":"deepseek/deepseek-v3.2","source":"huggingface","metric":"hf_downloads_30d","value":5289963,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V3.2"},{"modelId":"deepseek/deepseek-v3.2","source":"huggingface","metric":"hf_likes","value":1583,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V3.2"},{"modelId":"deepseek/deepseek-v3.2","source":"huggingface","metric":"hf_downloads_all_time","value":29789308,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V3.2"},{"modelId":"deepseek/deepseek-v3.2","source":"huggingface","metric":"hf_parameters","value":685355329792,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V3.2"},{"modelId":"moonshotai/kimi-k2-thinking","source":"huggingface","metric":"hf_downloads_30d","value":54866,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2-Thinking"},{"modelId":"moonshotai/kimi-k2-thinking","source":"huggingface","metric":"hf_likes","value":1727,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2-Thinking"},{"modelId":"moonshotai/kimi-k2-thinking","source":"huggingface","metric":"hf_trending","value":4,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2-Thinking"},{"modelId":"moonshotai/kimi-k2-thinking","source":"huggingface","metric":"hf_downloads_all_time","value":1947937,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2-Thinking"},{"modelId":"moonshotai/kimi-k2-thinking","source":"huggingface","metric":"hf_parameters","value":1026408240256,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2-Thinking"},{"modelId":"mistralai/voxtral-small-24b-2507","source":"huggingface","metric":"hf_downloads_30d","value":20742,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Voxtral-Small-24B-2507"},{"modelId":"mistralai/voxtral-small-24b-2507","source":"huggingface","metric":"hf_likes","value":542,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Voxtral-Small-24B-2507"},{"modelId":"mistralai/voxtral-small-24b-2507","source":"huggingface","metric":"hf_downloads_all_time","value":991851,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Voxtral-Small-24B-2507"},{"modelId":"mistralai/voxtral-small-24b-2507","source":"huggingface","metric":"hf_parameters","value":24261800960,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Voxtral-Small-24B-2507"},{"modelId":"openai/gpt-oss-safeguard-20b","source":"huggingface","metric":"hf_downloads_30d","value":22153,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/openai/gpt-oss-safeguard-20b"},{"modelId":"openai/gpt-oss-safeguard-20b","source":"huggingface","metric":"hf_likes","value":281,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/openai/gpt-oss-safeguard-20b"},{"modelId":"openai/gpt-oss-safeguard-20b","source":"huggingface","metric":"hf_trending","value":3,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/openai/gpt-oss-safeguard-20b"},{"modelId":"openai/gpt-oss-safeguard-20b","source":"huggingface","metric":"hf_downloads_all_time","value":805314,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/openai/gpt-oss-safeguard-20b"},{"modelId":"openai/gpt-oss-safeguard-20b","source":"huggingface","metric":"hf_parameters","value":21511953984,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/openai/gpt-oss-safeguard-20b"},{"modelId":"minimax/minimax-m2","source":"huggingface","metric":"hf_downloads_30d","value":149619,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2"},{"modelId":"minimax/minimax-m2","source":"huggingface","metric":"hf_likes","value":1509,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2"},{"modelId":"minimax/minimax-m2","source":"huggingface","metric":"hf_downloads_all_time","value":2954100,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2"},{"modelId":"minimax/minimax-m2","source":"huggingface","metric":"hf_parameters","value":228689764864,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M2"},{"modelId":"ibm-granite/granite-4.0-h-micro","source":"huggingface","metric":"hf_downloads_30d","value":9549,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/ibm-granite/granite-4.0-h-micro"},{"modelId":"ibm-granite/granite-4.0-h-micro","source":"huggingface","metric":"hf_likes","value":147,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/ibm-granite/granite-4.0-h-micro"},{"modelId":"ibm-granite/granite-4.0-h-micro","source":"huggingface","metric":"hf_trending","value":0,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/ibm-granite/granite-4.0-h-micro"},{"modelId":"ibm-granite/granite-4.0-h-micro","source":"huggingface","metric":"hf_downloads_all_time","value":253139,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/ibm-granite/granite-4.0-h-micro"},{"modelId":"ibm-granite/granite-4.0-h-micro","source":"huggingface","metric":"hf_parameters","value":3191396096,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/ibm-granite/granite-4.0-h-micro"},{"modelId":"qwen/qwen3-vl-8b-instruct","source":"huggingface","metric":"hf_downloads_30d","value":5785693,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct"},{"modelId":"qwen/qwen3-vl-8b-instruct","source":"huggingface","metric":"hf_likes","value":1214,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct"},{"modelId":"qwen/qwen3-vl-8b-instruct","source":"huggingface","metric":"hf_trending","value":15,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct"},{"modelId":"qwen/qwen3-vl-8b-instruct","source":"huggingface","metric":"hf_downloads_all_time","value":74240339,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct"},{"modelId":"qwen/qwen3-vl-8b-instruct","source":"huggingface","metric":"hf_parameters","value":8767123696,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct"},{"modelId":"qwen/qwen3-vl-30b-a3b-thinking","source":"huggingface","metric":"hf_downloads_30d","value":18864,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-VL-30B-A3B-Thinking"},{"modelId":"qwen/qwen3-vl-30b-a3b-thinking","source":"huggingface","metric":"hf_likes","value":205,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-VL-30B-A3B-Thinking"},{"modelId":"qwen/qwen3-vl-30b-a3b-thinking","source":"huggingface","metric":"hf_trending","value":0,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-VL-30B-A3B-Thinking"},{"modelId":"qwen/qwen3-vl-30b-a3b-thinking","source":"huggingface","metric":"hf_downloads_all_time","value":1055862,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-VL-30B-A3B-Thinking"},{"modelId":"qwen/qwen3-vl-30b-a3b-thinking","source":"huggingface","metric":"hf_parameters","value":31070754032,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-VL-30B-A3B-Thinking"},{"modelId":"qwen/qwen3-vl-30b-a3b-instruct","source":"huggingface","metric":"hf_downloads_30d","value":254335,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-VL-30B-A3B-Instruct"},{"modelId":"qwen/qwen3-vl-30b-a3b-instruct","source":"huggingface","metric":"hf_likes","value":618,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-VL-30B-A3B-Instruct"},{"modelId":"qwen/qwen3-vl-30b-a3b-instruct","source":"huggingface","metric":"hf_downloads_all_time","value":18156788,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-VL-30B-A3B-Instruct"},{"modelId":"qwen/qwen3-vl-30b-a3b-instruct","source":"huggingface","metric":"hf_parameters","value":31070754032,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-VL-30B-A3B-Instruct"},{"modelId":"z-ai/glm-4.6","source":"huggingface","metric":"hf_downloads_30d","value":19474,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-4.6"},{"modelId":"z-ai/glm-4.6","source":"huggingface","metric":"hf_likes","value":1241,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-4.6"},{"modelId":"z-ai/glm-4.6","source":"huggingface","metric":"hf_trending","value":0,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-4.6"},{"modelId":"z-ai/glm-4.6","source":"huggingface","metric":"hf_downloads_all_time","value":821741,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-4.6"},{"modelId":"z-ai/glm-4.6","source":"huggingface","metric":"hf_parameters","value":356785898816,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-4.6"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"huggingface","metric":"hf_downloads_30d","value":44072,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"huggingface","metric":"hf_likes","value":1022,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"huggingface","metric":"hf_trending","value":0,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"huggingface","metric":"hf_downloads_all_time","value":1566537,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"huggingface","metric":"hf_parameters","value":685396921376,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp"},{"modelId":"thedrummer/cydonia-24b-v4.1","source":"huggingface","metric":"hf_downloads_30d","value":3746,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/TheDrummer/Cydonia-24B-v4.1"},{"modelId":"thedrummer/cydonia-24b-v4.1","source":"huggingface","metric":"hf_likes","value":83,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/TheDrummer/Cydonia-24B-v4.1"},{"modelId":"thedrummer/cydonia-24b-v4.1","source":"huggingface","metric":"hf_trending","value":1,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/TheDrummer/Cydonia-24B-v4.1"},{"modelId":"thedrummer/cydonia-24b-v4.1","source":"huggingface","metric":"hf_downloads_all_time","value":26890,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/TheDrummer/Cydonia-24B-v4.1"},{"modelId":"thedrummer/cydonia-24b-v4.1","source":"huggingface","metric":"hf_parameters","value":23572403200,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/TheDrummer/Cydonia-24B-v4.1"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"huggingface","metric":"hf_downloads_30d","value":295269,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-VL-235B-A22B-Instruct"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"huggingface","metric":"hf_likes","value":425,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-VL-235B-A22B-Instruct"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"huggingface","metric":"hf_trending","value":0,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-VL-235B-A22B-Instruct"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"huggingface","metric":"hf_downloads_all_time","value":9739964,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-VL-235B-A22B-Instruct"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"huggingface","metric":"hf_parameters","value":235670022896,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-VL-235B-A22B-Instruct"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"huggingface","metric":"hf_downloads_30d","value":16217,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Terminus"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"huggingface","metric":"hf_likes","value":382,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Terminus"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"huggingface","metric":"hf_downloads_all_time","value":271290,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Terminus"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"huggingface","metric":"hf_parameters","value":684531386000,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Terminus"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"huggingface","metric":"hf_downloads_30d","value":39409,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Thinking"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"huggingface","metric":"hf_likes","value":500,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Thinking"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"huggingface","metric":"hf_trending","value":0,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Thinking"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"huggingface","metric":"hf_downloads_all_time","value":2534441,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Thinking"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"huggingface","metric":"hf_parameters","value":81324862720,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Thinking"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"huggingface","metric":"hf_downloads_30d","value":177508,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"huggingface","metric":"hf_likes","value":1065,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"huggingface","metric":"hf_downloads_all_time","value":16639297,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"huggingface","metric":"hf_parameters","value":81324862720,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct"},{"modelId":"moonshotai/kimi-k2-0905","source":"huggingface","metric":"hf_downloads_30d","value":47154,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2-Instruct-0905"},{"modelId":"moonshotai/kimi-k2-0905","source":"huggingface","metric":"hf_likes","value":790,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2-Instruct-0905"},{"modelId":"moonshotai/kimi-k2-0905","source":"huggingface","metric":"hf_trending","value":0,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2-Instruct-0905"},{"modelId":"moonshotai/kimi-k2-0905","source":"huggingface","metric":"hf_downloads_all_time","value":5208079,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2-Instruct-0905"},{"modelId":"moonshotai/kimi-k2-0905","source":"huggingface","metric":"hf_parameters","value":1026470735448,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2-Instruct-0905"},{"modelId":"nousresearch/hermes-4-405b","source":"huggingface","metric":"hf_downloads_30d","value":1122,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/NousResearch/Hermes-4-405B"},{"modelId":"nousresearch/hermes-4-405b","source":"huggingface","metric":"hf_likes","value":97,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/NousResearch/Hermes-4-405B"},{"modelId":"nousresearch/hermes-4-405b","source":"huggingface","metric":"hf_trending","value":0,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/NousResearch/Hermes-4-405B"},{"modelId":"nousresearch/hermes-4-405b","source":"huggingface","metric":"hf_downloads_all_time","value":7670,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/NousResearch/Hermes-4-405B"},{"modelId":"nousresearch/hermes-4-405b","source":"huggingface","metric":"hf_parameters","value":405853388800,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/NousResearch/Hermes-4-405B"},{"modelId":"deepseek/deepseek-chat-v3.1","source":"huggingface","metric":"hf_downloads_30d","value":335428,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V3.1"},{"modelId":"deepseek/deepseek-chat-v3.1","source":"huggingface","metric":"hf_likes","value":861,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V3.1"},{"modelId":"deepseek/deepseek-chat-v3.1","source":"huggingface","metric":"hf_trending","value":0,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V3.1"},{"modelId":"deepseek/deepseek-chat-v3.1","source":"huggingface","metric":"hf_downloads_all_time","value":3358454,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V3.1"},{"modelId":"deepseek/deepseek-chat-v3.1","source":"huggingface","metric":"hf_parameters","value":684531386000,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V3.1"},{"modelId":"z-ai/glm-4.5v","source":"huggingface","metric":"hf_downloads_30d","value":30002,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-4.5V"},{"modelId":"z-ai/glm-4.5v","source":"huggingface","metric":"hf_likes","value":724,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-4.5V"},{"modelId":"z-ai/glm-4.5v","source":"huggingface","metric":"hf_trending","value":0,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-4.5V"},{"modelId":"z-ai/glm-4.5v","source":"huggingface","metric":"hf_downloads_all_time","value":1072571,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-4.5V"},{"modelId":"z-ai/glm-4.5v","source":"huggingface","metric":"hf_parameters","value":107710933120,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-4.5V"},{"modelId":"openai/gpt-oss-120b","source":"huggingface","metric":"hf_downloads_30d","value":3181265,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/openai/gpt-oss-120b"},{"modelId":"openai/gpt-oss-120b","source":"huggingface","metric":"hf_likes","value":5426,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/openai/gpt-oss-120b"},{"modelId":"openai/gpt-oss-120b","source":"huggingface","metric":"hf_trending","value":28,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/openai/gpt-oss-120b"},{"modelId":"openai/gpt-oss-120b","source":"huggingface","metric":"hf_downloads_all_time","value":60162038,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/openai/gpt-oss-120b"},{"modelId":"openai/gpt-oss-120b","source":"huggingface","metric":"hf_parameters","value":116829156672,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/openai/gpt-oss-120b"},{"modelId":"openai/gpt-oss-20b","source":"huggingface","metric":"hf_downloads_30d","value":5897765,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/openai/gpt-oss-20b"},{"modelId":"openai/gpt-oss-20b","source":"huggingface","metric":"hf_likes","value":5192,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/openai/gpt-oss-20b"},{"modelId":"openai/gpt-oss-20b","source":"huggingface","metric":"hf_trending","value":18,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/openai/gpt-oss-20b"},{"modelId":"openai/gpt-oss-20b","source":"huggingface","metric":"hf_downloads_all_time","value":104343323,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/openai/gpt-oss-20b"},{"modelId":"openai/gpt-oss-20b","source":"huggingface","metric":"hf_parameters","value":20914757184,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/openai/gpt-oss-20b"},{"modelId":"qwen/qwen3-coder-30b-a3b-instruct","source":"huggingface","metric":"hf_downloads_30d","value":515009,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct"},{"modelId":"qwen/qwen3-coder-30b-a3b-instruct","source":"huggingface","metric":"hf_likes","value":1295,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct"},{"modelId":"qwen/qwen3-coder-30b-a3b-instruct","source":"huggingface","metric":"hf_trending","value":11,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct"},{"modelId":"qwen/qwen3-coder-30b-a3b-instruct","source":"huggingface","metric":"hf_downloads_all_time","value":15797436,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct"},{"modelId":"qwen/qwen3-coder-30b-a3b-instruct","source":"huggingface","metric":"hf_parameters","value":30532122624,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"huggingface","metric":"hf_downloads_30d","value":1075446,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"huggingface","metric":"hf_likes","value":848,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"huggingface","metric":"hf_trending","value":1,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"huggingface","metric":"hf_downloads_all_time","value":18173915,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"huggingface","metric":"hf_parameters","value":30532122624,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507"},{"modelId":"z-ai/glm-4.5","source":"huggingface","metric":"hf_downloads_30d","value":117655,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-4.5"},{"modelId":"z-ai/glm-4.5","source":"huggingface","metric":"hf_likes","value":1417,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-4.5"},{"modelId":"z-ai/glm-4.5","source":"huggingface","metric":"hf_downloads_all_time","value":1225717,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-4.5"},{"modelId":"z-ai/glm-4.5","source":"huggingface","metric":"hf_parameters","value":358337791296,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-4.5"},{"modelId":"z-ai/glm-4.5-air","source":"huggingface","metric":"hf_downloads_30d","value":755766,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-4.5-Air"},{"modelId":"z-ai/glm-4.5-air","source":"huggingface","metric":"hf_likes","value":646,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-4.5-Air"},{"modelId":"z-ai/glm-4.5-air","source":"huggingface","metric":"hf_trending","value":1,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-4.5-Air"},{"modelId":"z-ai/glm-4.5-air","source":"huggingface","metric":"hf_downloads_all_time","value":5413642,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-4.5-Air"},{"modelId":"z-ai/glm-4.5-air","source":"huggingface","metric":"hf_parameters","value":110468824832,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/zai-org/GLM-4.5-Air"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"huggingface","metric":"hf_downloads_30d","value":17609,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Thinking-2507"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"huggingface","metric":"hf_likes","value":416,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Thinking-2507"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"huggingface","metric":"hf_trending","value":0,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Thinking-2507"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"huggingface","metric":"hf_downloads_all_time","value":660909,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Thinking-2507"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"huggingface","metric":"hf_parameters","value":235093634560,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Thinking-2507"},{"modelId":"qwen/qwen3-coder","source":"huggingface","metric":"hf_downloads_30d","value":42009,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct"},{"modelId":"qwen/qwen3-coder","source":"huggingface","metric":"hf_likes","value":1382,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct"},{"modelId":"qwen/qwen3-coder","source":"huggingface","metric":"hf_trending","value":2,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct"},{"modelId":"qwen/qwen3-coder","source":"huggingface","metric":"hf_downloads_all_time","value":1169134,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct"},{"modelId":"qwen/qwen3-coder","source":"huggingface","metric":"hf_parameters","value":480154875392,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct"},{"modelId":"bytedance/ui-tars-1.5-7b","source":"huggingface","metric":"hf_downloads_30d","value":206466,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/ByteDance-Seed/UI-TARS-1.5-7B"},{"modelId":"bytedance/ui-tars-1.5-7b","source":"huggingface","metric":"hf_likes","value":612,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/ByteDance-Seed/UI-TARS-1.5-7B"},{"modelId":"bytedance/ui-tars-1.5-7b","source":"huggingface","metric":"hf_trending","value":1,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/ByteDance-Seed/UI-TARS-1.5-7B"},{"modelId":"bytedance/ui-tars-1.5-7b","source":"huggingface","metric":"hf_downloads_all_time","value":4491158,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/ByteDance-Seed/UI-TARS-1.5-7B"},{"modelId":"bytedance/ui-tars-1.5-7b","source":"huggingface","metric":"hf_parameters","value":8292166656,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/ByteDance-Seed/UI-TARS-1.5-7B"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"huggingface","metric":"hf_downloads_30d","value":155964,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"huggingface","metric":"hf_likes","value":811,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"huggingface","metric":"hf_trending","value":1,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"huggingface","metric":"hf_downloads_all_time","value":1916563,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"huggingface","metric":"hf_parameters","value":235093634560,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507"},{"modelId":"moonshotai/kimi-k2","source":"huggingface","metric":"hf_downloads_30d","value":345520,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2-Instruct"},{"modelId":"moonshotai/kimi-k2","source":"huggingface","metric":"hf_likes","value":3004,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2-Instruct"},{"modelId":"moonshotai/kimi-k2","source":"huggingface","metric":"hf_downloads_all_time","value":4490965,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2-Instruct"},{"modelId":"moonshotai/kimi-k2","source":"huggingface","metric":"hf_parameters","value":1026408235864,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2-Instruct"},{"modelId":"cognitivecomputations/dolphin-mistral-24b-venice-edition","source":"huggingface","metric":"hf_downloads_30d","value":7607,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/dphn/Dolphin-Mistral-24B-Venice-Edition"},{"modelId":"cognitivecomputations/dolphin-mistral-24b-venice-edition","source":"huggingface","metric":"hf_likes","value":756,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/dphn/Dolphin-Mistral-24B-Venice-Edition"},{"modelId":"cognitivecomputations/dolphin-mistral-24b-venice-edition","source":"huggingface","metric":"hf_trending","value":5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/dphn/Dolphin-Mistral-24B-Venice-Edition"},{"modelId":"cognitivecomputations/dolphin-mistral-24b-venice-edition","source":"huggingface","metric":"hf_downloads_all_time","value":1035696,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/dphn/Dolphin-Mistral-24B-Venice-Edition"},{"modelId":"cognitivecomputations/dolphin-mistral-24b-venice-edition","source":"huggingface","metric":"hf_parameters","value":24011361280,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/dphn/Dolphin-Mistral-24B-Venice-Edition"},{"modelId":"tencent/hunyuan-a13b-instruct","source":"huggingface","metric":"hf_downloads_30d","value":69934,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/tencent/Hunyuan-A13B-Instruct"},{"modelId":"tencent/hunyuan-a13b-instruct","source":"huggingface","metric":"hf_likes","value":795,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/tencent/Hunyuan-A13B-Instruct"},{"modelId":"tencent/hunyuan-a13b-instruct","source":"huggingface","metric":"hf_trending","value":0,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/tencent/Hunyuan-A13B-Instruct"},{"modelId":"tencent/hunyuan-a13b-instruct","source":"huggingface","metric":"hf_downloads_all_time","value":485644,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/tencent/Hunyuan-A13B-Instruct"},{"modelId":"tencent/hunyuan-a13b-instruct","source":"huggingface","metric":"hf_parameters","value":80393183232,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/tencent/Hunyuan-A13B-Instruct"},{"modelId":"mistralai/mistral-small-3.2-24b-instruct","source":"huggingface","metric":"hf_downloads_30d","value":208652,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506"},{"modelId":"mistralai/mistral-small-3.2-24b-instruct","source":"huggingface","metric":"hf_likes","value":638,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506"},{"modelId":"mistralai/mistral-small-3.2-24b-instruct","source":"huggingface","metric":"hf_trending","value":1,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506"},{"modelId":"mistralai/mistral-small-3.2-24b-instruct","source":"huggingface","metric":"hf_downloads_all_time","value":5558129,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506"},{"modelId":"mistralai/mistral-small-3.2-24b-instruct","source":"huggingface","metric":"hf_parameters","value":24011361280,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506"},{"modelId":"deepseek/deepseek-r1-0528","source":"huggingface","metric":"hf_downloads_30d","value":174784,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-R1-0528"},{"modelId":"deepseek/deepseek-r1-0528","source":"huggingface","metric":"hf_likes","value":2488,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-R1-0528"},{"modelId":"deepseek/deepseek-r1-0528","source":"huggingface","metric":"hf_downloads_all_time","value":17036646,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-R1-0528"},{"modelId":"deepseek/deepseek-r1-0528","source":"huggingface","metric":"hf_parameters","value":684531386000,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-R1-0528"},{"modelId":"meta-llama/llama-guard-4-12b","source":"huggingface","metric":"hf_downloads_30d","value":47242,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-Guard-4-12B"},{"modelId":"meta-llama/llama-guard-4-12b","source":"huggingface","metric":"hf_likes","value":133,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-Guard-4-12B"},{"modelId":"meta-llama/llama-guard-4-12b","source":"huggingface","metric":"hf_trending","value":2,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-Guard-4-12B"},{"modelId":"meta-llama/llama-guard-4-12b","source":"huggingface","metric":"hf_downloads_all_time","value":1569029,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-Guard-4-12B"},{"modelId":"meta-llama/llama-guard-4-12b","source":"huggingface","metric":"hf_parameters","value":12001097216,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-Guard-4-12B"},{"modelId":"qwen/qwen3-30b-a3b","source":"huggingface","metric":"hf_downloads_30d","value":1145092,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-30B-A3B"},{"modelId":"qwen/qwen3-30b-a3b","source":"huggingface","metric":"hf_likes","value":968,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-30B-A3B"},{"modelId":"qwen/qwen3-30b-a3b","source":"huggingface","metric":"hf_trending","value":2,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-30B-A3B"},{"modelId":"qwen/qwen3-30b-a3b","source":"huggingface","metric":"hf_downloads_all_time","value":22321080,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-30B-A3B"},{"modelId":"qwen/qwen3-30b-a3b","source":"huggingface","metric":"hf_parameters","value":30532122624,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-30B-A3B"},{"modelId":"qwen/qwen3-14b","source":"huggingface","metric":"hf_downloads_30d","value":8407150,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-14B"},{"modelId":"qwen/qwen3-14b","source":"huggingface","metric":"hf_likes","value":510,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-14B"},{"modelId":"qwen/qwen3-14b","source":"huggingface","metric":"hf_trending","value":6,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-14B"},{"modelId":"qwen/qwen3-14b","source":"huggingface","metric":"hf_downloads_all_time","value":36686461,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-14B"},{"modelId":"qwen/qwen3-14b","source":"huggingface","metric":"hf_parameters","value":14768307200,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-14B"},{"modelId":"qwen/qwen3-32b","source":"huggingface","metric":"hf_downloads_30d","value":2905251,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-32B"},{"modelId":"qwen/qwen3-32b","source":"huggingface","metric":"hf_likes","value":769,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-32B"},{"modelId":"qwen/qwen3-32b","source":"huggingface","metric":"hf_downloads_all_time","value":60366389,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-32B"},{"modelId":"qwen/qwen3-32b","source":"huggingface","metric":"hf_parameters","value":32762123264,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen3-32B"},{"modelId":"meta-llama/llama-4-maverick","source":"huggingface","metric":"hf_downloads_30d","value":9859,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct"},{"modelId":"meta-llama/llama-4-maverick","source":"huggingface","metric":"hf_likes","value":516,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct"},{"modelId":"meta-llama/llama-4-maverick","source":"huggingface","metric":"hf_trending","value":0,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct"},{"modelId":"meta-llama/llama-4-maverick","source":"huggingface","metric":"hf_downloads_all_time","value":747474,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct"},{"modelId":"meta-llama/llama-4-maverick","source":"huggingface","metric":"hf_parameters","value":401583781376,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct"},{"modelId":"meta-llama/llama-4-scout","source":"huggingface","metric":"hf_downloads_30d","value":156409,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct"},{"modelId":"meta-llama/llama-4-scout","source":"huggingface","metric":"hf_likes","value":1378,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct"},{"modelId":"meta-llama/llama-4-scout","source":"huggingface","metric":"hf_trending","value":2,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct"},{"modelId":"meta-llama/llama-4-scout","source":"huggingface","metric":"hf_downloads_all_time","value":7821289,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct"},{"modelId":"meta-llama/llama-4-scout","source":"huggingface","metric":"hf_parameters","value":108641793536,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"huggingface","metric":"hf_downloads_30d","value":1084468,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V3-0324"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"huggingface","metric":"hf_likes","value":3221,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V3-0324"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"huggingface","metric":"hf_trending","value":0,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V3-0324"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"huggingface","metric":"hf_downloads_all_time","value":10439792,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V3-0324"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"huggingface","metric":"hf_parameters","value":684531386000,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V3-0324"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"huggingface","metric":"hf_downloads_30d","value":279667,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"huggingface","metric":"hf_likes","value":1404,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"huggingface","metric":"hf_trending","value":0,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"huggingface","metric":"hf_downloads_all_time","value":4659701,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"huggingface","metric":"hf_parameters","value":24011361280,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503"},{"modelId":"google/gemma-3-4b-it","source":"huggingface","metric":"hf_downloads_30d","value":1077108,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/google/gemma-3-4b-it"},{"modelId":"google/gemma-3-4b-it","source":"huggingface","metric":"hf_likes","value":1585,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/google/gemma-3-4b-it"},{"modelId":"google/gemma-3-4b-it","source":"huggingface","metric":"hf_trending","value":5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/google/gemma-3-4b-it"},{"modelId":"google/gemma-3-4b-it","source":"huggingface","metric":"hf_downloads_all_time","value":27336235,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/google/gemma-3-4b-it"},{"modelId":"google/gemma-3-4b-it","source":"huggingface","metric":"hf_parameters","value":4300079472,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/google/gemma-3-4b-it"},{"modelId":"google/gemma-3-12b-it","source":"huggingface","metric":"hf_downloads_30d","value":361405,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/google/gemma-3-12b-it"},{"modelId":"google/gemma-3-12b-it","source":"huggingface","metric":"hf_likes","value":878,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/google/gemma-3-12b-it"},{"modelId":"google/gemma-3-12b-it","source":"huggingface","metric":"hf_trending","value":5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/google/gemma-3-12b-it"},{"modelId":"google/gemma-3-12b-it","source":"huggingface","metric":"hf_downloads_all_time","value":23210069,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/google/gemma-3-12b-it"},{"modelId":"google/gemma-3-12b-it","source":"huggingface","metric":"hf_parameters","value":12187325040,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/google/gemma-3-12b-it"},{"modelId":"cohere/command-a","source":"huggingface","metric":"hf_downloads_30d","value":1529,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/CohereLabs/c4ai-command-a-03-2025"},{"modelId":"cohere/command-a","source":"huggingface","metric":"hf_likes","value":397,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/CohereLabs/c4ai-command-a-03-2025"},{"modelId":"cohere/command-a","source":"huggingface","metric":"hf_trending","value":0,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/CohereLabs/c4ai-command-a-03-2025"},{"modelId":"cohere/command-a","source":"huggingface","metric":"hf_downloads_all_time","value":126027,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/CohereLabs/c4ai-command-a-03-2025"},{"modelId":"cohere/command-a","source":"huggingface","metric":"hf_parameters","value":111057580032,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/CohereLabs/c4ai-command-a-03-2025"},{"modelId":"rekaai/reka-flash-3","source":"huggingface","metric":"hf_downloads_30d","value":808,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/RekaAI/reka-flash-3"},{"modelId":"rekaai/reka-flash-3","source":"huggingface","metric":"hf_likes","value":389,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/RekaAI/reka-flash-3"},{"modelId":"rekaai/reka-flash-3","source":"huggingface","metric":"hf_trending","value":0,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/RekaAI/reka-flash-3"},{"modelId":"rekaai/reka-flash-3","source":"huggingface","metric":"hf_downloads_all_time","value":22565,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/RekaAI/reka-flash-3"},{"modelId":"rekaai/reka-flash-3","source":"huggingface","metric":"hf_parameters","value":20905482240,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/RekaAI/reka-flash-3"},{"modelId":"google/gemma-3-27b-it","source":"huggingface","metric":"hf_downloads_30d","value":391853,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/google/gemma-3-27b-it"},{"modelId":"google/gemma-3-27b-it","source":"huggingface","metric":"hf_likes","value":2052,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/google/gemma-3-27b-it"},{"modelId":"google/gemma-3-27b-it","source":"huggingface","metric":"hf_trending","value":4,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/google/gemma-3-27b-it"},{"modelId":"google/gemma-3-27b-it","source":"huggingface","metric":"hf_downloads_all_time","value":17492034,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/google/gemma-3-27b-it"},{"modelId":"google/gemma-3-27b-it","source":"huggingface","metric":"hf_parameters","value":27432406640,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/google/gemma-3-27b-it"},{"modelId":"thedrummer/skyfall-36b-v2","source":"huggingface","metric":"hf_downloads_30d","value":3574,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/TheDrummer/Skyfall-36B-v2"},{"modelId":"thedrummer/skyfall-36b-v2","source":"huggingface","metric":"hf_likes","value":54,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/TheDrummer/Skyfall-36B-v2"},{"modelId":"thedrummer/skyfall-36b-v2","source":"huggingface","metric":"hf_trending","value":0,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/TheDrummer/Skyfall-36B-v2"},{"modelId":"thedrummer/skyfall-36b-v2","source":"huggingface","metric":"hf_downloads_all_time","value":19344,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/TheDrummer/Skyfall-36B-v2"},{"modelId":"thedrummer/skyfall-36b-v2","source":"huggingface","metric":"hf_parameters","value":36910535680,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/TheDrummer/Skyfall-36B-v2"},{"modelId":"qwen/qwen2.5-vl-72b-instruct","source":"huggingface","metric":"hf_downloads_30d","value":66671,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct"},{"modelId":"qwen/qwen2.5-vl-72b-instruct","source":"huggingface","metric":"hf_likes","value":661,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct"},{"modelId":"qwen/qwen2.5-vl-72b-instruct","source":"huggingface","metric":"hf_trending","value":0,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct"},{"modelId":"qwen/qwen2.5-vl-72b-instruct","source":"huggingface","metric":"hf_downloads_all_time","value":7656205,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct"},{"modelId":"qwen/qwen2.5-vl-72b-instruct","source":"huggingface","metric":"hf_parameters","value":73410777344,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"huggingface","metric":"hf_downloads_30d","value":69904,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"huggingface","metric":"hf_likes","value":983,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"huggingface","metric":"hf_trending","value":0,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"huggingface","metric":"hf_downloads_all_time","value":7370855,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"huggingface","metric":"hf_parameters","value":23572403200,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501"},{"modelId":"minimax/minimax-01","source":"huggingface","metric":"hf_downloads_30d","value":2599,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-Text-01"},{"modelId":"minimax/minimax-01","source":"huggingface","metric":"hf_likes","value":656,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-Text-01"},{"modelId":"minimax/minimax-01","source":"huggingface","metric":"hf_trending","value":0,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-Text-01"},{"modelId":"minimax/minimax-01","source":"huggingface","metric":"hf_downloads_all_time","value":91326,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-Text-01"},{"modelId":"minimax/minimax-01","source":"huggingface","metric":"hf_parameters","value":456089655296,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-Text-01"},{"modelId":"microsoft/phi-4","source":"huggingface","metric":"hf_downloads_30d","value":366104,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/microsoft/phi-4"},{"modelId":"microsoft/phi-4","source":"huggingface","metric":"hf_likes","value":2326,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/microsoft/phi-4"},{"modelId":"microsoft/phi-4","source":"huggingface","metric":"hf_trending","value":5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/microsoft/phi-4"},{"modelId":"microsoft/phi-4","source":"huggingface","metric":"hf_downloads_all_time","value":14742812,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/microsoft/phi-4"},{"modelId":"microsoft/phi-4","source":"huggingface","metric":"hf_parameters","value":14659507200,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/microsoft/phi-4"},{"modelId":"deepseek/deepseek-chat","source":"huggingface","metric":"hf_downloads_30d","value":1368479,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V3"},{"modelId":"deepseek/deepseek-chat","source":"huggingface","metric":"hf_likes","value":4447,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V3"},{"modelId":"deepseek/deepseek-chat","source":"huggingface","metric":"hf_downloads_all_time","value":22381656,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V3"},{"modelId":"deepseek/deepseek-chat","source":"huggingface","metric":"hf_parameters","value":684489845504,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V3"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"huggingface","metric":"hf_downloads_30d","value":239043,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"huggingface","metric":"hf_likes","value":3146,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"huggingface","metric":"hf_trending","value":10,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"huggingface","metric":"hf_downloads_all_time","value":14796883,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"huggingface","metric":"hf_parameters","value":70553706496,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"huggingface","metric":"hf_downloads_30d","value":653160,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"huggingface","metric":"hf_likes","value":2179,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"huggingface","metric":"hf_trending","value":1,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"huggingface","metric":"hf_downloads_all_time","value":13658600,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"huggingface","metric":"hf_parameters","value":32763876352,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct"},{"modelId":"thedrummer/unslopnemo-12b","source":"huggingface","metric":"hf_downloads_30d","value":1803,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/TheDrummer/UnslopNemo-12B-v4.1"},{"modelId":"thedrummer/unslopnemo-12b","source":"huggingface","metric":"hf_likes","value":25,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/TheDrummer/UnslopNemo-12B-v4.1"},{"modelId":"thedrummer/unslopnemo-12b","source":"huggingface","metric":"hf_trending","value":0,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/TheDrummer/UnslopNemo-12B-v4.1"},{"modelId":"thedrummer/unslopnemo-12b","source":"huggingface","metric":"hf_downloads_all_time","value":260454,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/TheDrummer/UnslopNemo-12B-v4.1"},{"modelId":"thedrummer/unslopnemo-12b","source":"huggingface","metric":"hf_parameters","value":12247782400,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/TheDrummer/UnslopNemo-12B-v4.1"},{"modelId":"anthracite-org/magnum-v4-72b","source":"huggingface","metric":"hf_downloads_30d","value":805,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/anthracite-org/magnum-v4-72b"},{"modelId":"anthracite-org/magnum-v4-72b","source":"huggingface","metric":"hf_likes","value":64,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/anthracite-org/magnum-v4-72b"},{"modelId":"anthracite-org/magnum-v4-72b","source":"huggingface","metric":"hf_trending","value":0,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/anthracite-org/magnum-v4-72b"},{"modelId":"anthracite-org/magnum-v4-72b","source":"huggingface","metric":"hf_downloads_all_time","value":49361,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/anthracite-org/magnum-v4-72b"},{"modelId":"anthracite-org/magnum-v4-72b","source":"huggingface","metric":"hf_parameters","value":72706203648,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/anthracite-org/magnum-v4-72b"},{"modelId":"qwen/qwen-2.5-7b-instruct","source":"huggingface","metric":"hf_downloads_30d","value":6777731,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen2.5-7B-Instruct"},{"modelId":"qwen/qwen-2.5-7b-instruct","source":"huggingface","metric":"hf_likes","value":2446,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen2.5-7B-Instruct"},{"modelId":"qwen/qwen-2.5-7b-instruct","source":"huggingface","metric":"hf_trending","value":4,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen2.5-7B-Instruct"},{"modelId":"qwen/qwen-2.5-7b-instruct","source":"huggingface","metric":"hf_downloads_all_time","value":189245093,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen2.5-7B-Instruct"},{"modelId":"qwen/qwen-2.5-7b-instruct","source":"huggingface","metric":"hf_parameters","value":7615616512,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen2.5-7B-Instruct"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"huggingface","metric":"hf_downloads_30d","value":5072769,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"huggingface","metric":"hf_likes","value":1866,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"huggingface","metric":"hf_trending","value":20,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"huggingface","metric":"hf_downloads_all_time","value":108866632,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"huggingface","metric":"hf_parameters","value":1235814400,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"huggingface","metric":"hf_downloads_30d","value":1169655,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"huggingface","metric":"hf_likes","value":2829,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"huggingface","metric":"hf_trending","value":26,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"huggingface","metric":"hf_downloads_all_time","value":50252061,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"huggingface","metric":"hf_parameters","value":3212749824,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"huggingface","metric":"hf_downloads_30d","value":252898,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen2.5-72B-Instruct"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"huggingface","metric":"hf_likes","value":1017,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen2.5-72B-Instruct"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"huggingface","metric":"hf_trending","value":1,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen2.5-72B-Instruct"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"huggingface","metric":"hf_downloads_all_time","value":9038106,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen2.5-72B-Instruct"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"huggingface","metric":"hf_parameters","value":72706203648,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Qwen/Qwen2.5-72B-Instruct"},{"modelId":"sao10k/l3.1-euryale-70b","source":"huggingface","metric":"hf_downloads_30d","value":465,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Sao10K/L3.1-70B-Euryale-v2.2"},{"modelId":"sao10k/l3.1-euryale-70b","source":"huggingface","metric":"hf_likes","value":69,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Sao10K/L3.1-70B-Euryale-v2.2"},{"modelId":"sao10k/l3.1-euryale-70b","source":"huggingface","metric":"hf_trending","value":0,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Sao10K/L3.1-70B-Euryale-v2.2"},{"modelId":"sao10k/l3.1-euryale-70b","source":"huggingface","metric":"hf_downloads_all_time","value":16072,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Sao10K/L3.1-70B-Euryale-v2.2"},{"modelId":"nousresearch/hermes-3-llama-3.1-70b","source":"huggingface","metric":"hf_downloads_30d","value":2102,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-70B"},{"modelId":"nousresearch/hermes-3-llama-3.1-70b","source":"huggingface","metric":"hf_likes","value":144,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-70B"},{"modelId":"nousresearch/hermes-3-llama-3.1-70b","source":"huggingface","metric":"hf_trending","value":0,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-70B"},{"modelId":"nousresearch/hermes-3-llama-3.1-70b","source":"huggingface","metric":"hf_downloads_all_time","value":333865,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-70B"},{"modelId":"nousresearch/hermes-3-llama-3.1-70b","source":"huggingface","metric":"hf_parameters","value":70553706496,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-70B"},{"modelId":"nousresearch/hermes-3-llama-3.1-405b","source":"huggingface","metric":"hf_downloads_30d","value":1192,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-405B"},{"modelId":"nousresearch/hermes-3-llama-3.1-405b","source":"huggingface","metric":"hf_likes","value":275,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-405B"},{"modelId":"nousresearch/hermes-3-llama-3.1-405b","source":"huggingface","metric":"hf_trending","value":0,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-405B"},{"modelId":"nousresearch/hermes-3-llama-3.1-405b","source":"huggingface","metric":"hf_downloads_all_time","value":957881,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-405B"},{"modelId":"nousresearch/hermes-3-llama-3.1-405b","source":"huggingface","metric":"hf_parameters","value":405853388800,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-405B"},{"modelId":"sao10k/l3-lunaris-8b","source":"huggingface","metric":"hf_downloads_30d","value":1643,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Sao10K/L3-8B-Lunaris-v1"},{"modelId":"sao10k/l3-lunaris-8b","source":"huggingface","metric":"hf_likes","value":147,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Sao10K/L3-8B-Lunaris-v1"},{"modelId":"sao10k/l3-lunaris-8b","source":"huggingface","metric":"hf_trending","value":0,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Sao10K/L3-8B-Lunaris-v1"},{"modelId":"sao10k/l3-lunaris-8b","source":"huggingface","metric":"hf_downloads_all_time","value":458320,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Sao10K/L3-8B-Lunaris-v1"},{"modelId":"sao10k/l3-lunaris-8b","source":"huggingface","metric":"hf_parameters","value":8030261248,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Sao10K/L3-8B-Lunaris-v1"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"huggingface","metric":"hf_downloads_30d","value":87315,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"huggingface","metric":"hf_likes","value":1011,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"huggingface","metric":"hf_trending","value":1,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"huggingface","metric":"hf_downloads_all_time","value":24553939,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"huggingface","metric":"hf_parameters","value":70553706496,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"huggingface","metric":"hf_downloads_30d","value":5490624,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"huggingface","metric":"hf_likes","value":8514,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"huggingface","metric":"hf_trending","value":65,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"huggingface","metric":"hf_downloads_all_time","value":190555927,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"huggingface","metric":"hf_parameters","value":8030261248,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct"},{"modelId":"mistralai/mistral-nemo","source":"huggingface","metric":"hf_downloads_30d","value":217670,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407"},{"modelId":"mistralai/mistral-nemo","source":"huggingface","metric":"hf_likes","value":1734,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407"},{"modelId":"mistralai/mistral-nemo","source":"huggingface","metric":"hf_trending","value":2,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407"},{"modelId":"mistralai/mistral-nemo","source":"huggingface","metric":"hf_downloads_all_time","value":10616071,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407"},{"modelId":"mistralai/mistral-nemo","source":"huggingface","metric":"hf_parameters","value":12247782400,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407"},{"modelId":"google/gemma-2-27b-it","source":"huggingface","metric":"hf_downloads_30d","value":19281,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/google/gemma-2-27b-it"},{"modelId":"google/gemma-2-27b-it","source":"huggingface","metric":"hf_likes","value":577,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/google/gemma-2-27b-it"},{"modelId":"google/gemma-2-27b-it","source":"huggingface","metric":"hf_trending","value":0,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/google/gemma-2-27b-it"},{"modelId":"google/gemma-2-27b-it","source":"huggingface","metric":"hf_downloads_all_time","value":5348912,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/google/gemma-2-27b-it"},{"modelId":"google/gemma-2-27b-it","source":"huggingface","metric":"hf_parameters","value":27227128320,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/google/gemma-2-27b-it"},{"modelId":"mistralai/mixtral-8x22b-instruct","source":"huggingface","metric":"hf_downloads_30d","value":44326,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1"},{"modelId":"mistralai/mixtral-8x22b-instruct","source":"huggingface","metric":"hf_likes","value":775,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1"},{"modelId":"mistralai/mixtral-8x22b-instruct","source":"huggingface","metric":"hf_downloads_all_time","value":6335950,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1"},{"modelId":"mistralai/mixtral-8x22b-instruct","source":"huggingface","metric":"hf_parameters","value":140630071296,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1"},{"modelId":"undi95/remm-slerp-l2-13b","source":"huggingface","metric":"hf_downloads_30d","value":649,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Undi95/ReMM-SLERP-L2-13B"},{"modelId":"undi95/remm-slerp-l2-13b","source":"huggingface","metric":"hf_likes","value":28,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Undi95/ReMM-SLERP-L2-13B"},{"modelId":"undi95/remm-slerp-l2-13b","source":"huggingface","metric":"hf_trending","value":1,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Undi95/ReMM-SLERP-L2-13B"},{"modelId":"undi95/remm-slerp-l2-13b","source":"huggingface","metric":"hf_downloads_all_time","value":86471,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Undi95/ReMM-SLERP-L2-13B"},{"modelId":"gryphe/mythomax-l2-13b","source":"huggingface","metric":"hf_downloads_30d","value":1300,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Gryphe/MythoMax-L2-13b"},{"modelId":"gryphe/mythomax-l2-13b","source":"huggingface","metric":"hf_likes","value":408,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Gryphe/MythoMax-L2-13b"},{"modelId":"gryphe/mythomax-l2-13b","source":"huggingface","metric":"hf_trending","value":0,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Gryphe/MythoMax-L2-13b"},{"modelId":"gryphe/mythomax-l2-13b","source":"huggingface","metric":"hf_downloads_all_time","value":740323,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://huggingface.co/Gryphe/MythoMax-L2-13b"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_terminal_bench","value":0.847191011236,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_terminal_bench","value":0.818,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_terminal_bench","value":0.8022471910110001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"anthropic/claude-opus-4.7","source":"epoch","metric":"epoch_terminal_bench","value":0.8022471910110001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"anthropic/claude-opus-4.6","source":"epoch","metric":"epoch_terminal_bench","value":0.798,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"openai/gpt-5.3-codex","source":"epoch","metric":"epoch_terminal_bench","value":0.7842696629210001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"openai/gpt-5.2-codex","source":"epoch","metric":"epoch_terminal_bench","value":0.6651685393260001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"openai/gpt-5.2","source":"epoch","metric":"epoch_terminal_bench","value":0.6494382022470001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"google/gemini-3-flash-preview","source":"epoch","metric":"epoch_terminal_bench","value":0.642696629213,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_terminal_bench","value":0.631460674157,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"openai/gpt-5.1-codex-mini","source":"epoch","metric":"epoch_terminal_bench","value":0.615730337079,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"openai/gpt-5.1-codex-max","source":"epoch","metric":"epoch_terminal_bench","value":0.604494382022,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"openai/gpt-5.1-codex","source":"epoch","metric":"epoch_terminal_bench","value":0.578,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"x-ai/grok-4.20","source":"epoch","metric":"epoch_terminal_bench","value":0.573033707865,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"anthropic/claude-sonnet-4.6","source":"epoch","metric":"epoch_terminal_bench","value":0.534269662921,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"z-ai/glm-5","source":"epoch","metric":"epoch_terminal_bench","value":0.524157303371,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_terminal_bench","value":0.49606741573,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"openai/gpt-5.1","source":"epoch","metric":"epoch_terminal_bench","value":0.476,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"anthropic/claude-sonnet-4.5","source":"epoch","metric":"epoch_terminal_bench","value":0.465168539326,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"minimax/minimax-m2.7","source":"epoch","metric":"epoch_terminal_bench","value":0.45056179775300004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"moonshotai/kimi-k2.5","source":"epoch","metric":"epoch_terminal_bench","value":0.43202247191,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"minimax/minimax-m2.5","source":"epoch","metric":"epoch_terminal_bench","value":0.42696629213500004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"deepseek/deepseek-v3.2","source":"epoch","metric":"epoch_terminal_bench","value":0.395505617978,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"anthropic/claude-opus-4.1","source":"epoch","metric":"epoch_terminal_bench","value":0.38,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"minimax/minimax-m2.1","source":"epoch","metric":"epoch_terminal_bench","value":0.36629213483100004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"moonshotai/kimi-k2-thinking","source":"epoch","metric":"epoch_terminal_bench","value":0.35730337078700003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"anthropic/claude-haiku-4.5","source":"epoch","metric":"epoch_terminal_bench","value":0.35505617977500004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_terminal_bench","value":0.34831460674200004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"z-ai/glm-4.7","source":"epoch","metric":"epoch_terminal_bench","value":0.333895131086,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"google/gemini-2.5-pro","source":"epoch","metric":"epoch_terminal_bench","value":0.32640449438200003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"minimax/minimax-m2","source":"epoch","metric":"epoch_terminal_bench","value":0.300374531835,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"moonshotai/kimi-k2","source":"epoch","metric":"epoch_terminal_bench","value":0.278,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"qwen/qwen3-coder","source":"epoch","metric":"epoch_terminal_bench","value":0.27191011236,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"qwen/qwen3.6-35b-a3b","source":"epoch","metric":"epoch_terminal_bench","value":0.24625468164800002,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"z-ai/glm-4.6","source":"epoch","metric":"epoch_terminal_bench","value":0.24531835206,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"openai/gpt-5-nano","source":"epoch","metric":"epoch_terminal_bench","value":0.21797752808999998,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"openai/gpt-oss-120b","source":"epoch","metric":"epoch_terminal_bench","value":0.187,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"google/gemini-2.5-flash","source":"epoch","metric":"epoch_terminal_bench","value":0.170786516854,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"qwen/qwen3.5-9b","source":"epoch","metric":"epoch_terminal_bench","value":0.092134831461,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"openai/gpt-oss-20b","source":"epoch","metric":"epoch_terminal_bench","value":0.034,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.0"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_deepswe","value":0.7266666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_deepswe_cost_usd","value":8.386436,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_deepswe_pass_at_4","value":0.858407,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_deepswe_output_tokens","value":60013.644444,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_deepswe_agent_steps","value":61.253333,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_deepswe","value":0.6991150442477876,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_deepswe_cost_usd","value":13.414521,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_deepswe_pass_at_4","value":0.884956,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_deepswe_output_tokens","value":80352.170354,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_deepswe_agent_steps","value":68.400442,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_deepswe","value":0.6962305986696231,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_deepswe_cost_usd","value":4.945847,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_deepswe_pass_at_4","value":0.884956,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_deepswe_output_tokens","value":71938.625277,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_deepswe_agent_steps","value":75.929047,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_deepswe","value":0.671875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_deepswe_cost_usd","value":3.028117,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_deepswe_pass_at_4","value":0.902655,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_deepswe_output_tokens","value":73399.707589,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_deepswe_agent_steps","value":101.680804,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_deepswe","value":0.6703539823008849,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_deepswe_cost_usd","value":7.226237,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_deepswe_pass_at_4","value":0.884956,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_deepswe_output_tokens","value":46294.723451,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_deepswe_agent_steps","value":82.015487,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_deepswe","value":0.5897435897435898,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_deepswe_cost_usd","value":13.222584,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_deepswe_pass_at_4","value":0.792793,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_deepswe_output_tokens","value":135031.671329,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_deepswe_agent_steps","value":120,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"anthropic/claude-sonnet-5","source":"epoch","metric":"epoch_deepswe","value":0.5384615384615384,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"anthropic/claude-sonnet-5","source":"epoch","metric":"epoch_deepswe_cost_usd","value":26.399859,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"anthropic/claude-sonnet-5","source":"epoch","metric":"epoch_deepswe_pass_at_4","value":0.787611,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"anthropic/claude-sonnet-5","source":"epoch","metric":"epoch_deepswe_output_tokens","value":214117.549774,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"anthropic/claude-sonnet-5","source":"epoch","metric":"epoch_deepswe_agent_steps","value":268.454751,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"meta/muse-spark-1.1","source":"epoch","metric":"epoch_deepswe","value":0.5331858407079646,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"meta/muse-spark-1.1","source":"epoch","metric":"epoch_deepswe_cost_usd","value":2.361143,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"meta/muse-spark-1.1","source":"epoch","metric":"epoch_deepswe_pass_at_4","value":0.79646,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"meta/muse-spark-1.1","source":"epoch","metric":"epoch_deepswe_output_tokens","value":74008.420354,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"meta/muse-spark-1.1","source":"epoch","metric":"epoch_deepswe_agent_steps","value":95.825221,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_deepswe","value":0.5176991150442478,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_deepswe_cost_usd","value":5.652458,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_deepswe_pass_at_4","value":0.778761,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_deepswe_output_tokens","value":71408.873894,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_deepswe_agent_steps","value":70.471239,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_deepswe","value":0.4377777777777778,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_deepswe_cost_usd","value":3.919908,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_deepswe_pass_at_4","value":0.769912,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_deepswe_output_tokens","value":78175.306667,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_deepswe_agent_steps","value":129.126667,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"moonshotai/kimi-k2.7-code","source":"epoch","metric":"epoch_deepswe","value":0.3053097345132743,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"moonshotai/kimi-k2.7-code","source":"epoch","metric":"epoch_deepswe_cost_usd","value":2.815536,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"moonshotai/kimi-k2.7-code","source":"epoch","metric":"epoch_deepswe_pass_at_4","value":0.610619,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"moonshotai/kimi-k2.7-code","source":"epoch","metric":"epoch_deepswe_output_tokens","value":59297.247788,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"moonshotai/kimi-k2.7-code","source":"epoch","metric":"epoch_deepswe_agent_steps","value":149.115044,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"anthropic/claude-sonnet-4.6","source":"epoch","metric":"epoch_deepswe","value":0.29933481152993346,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"anthropic/claude-sonnet-4.6","source":"epoch","metric":"epoch_deepswe_cost_usd","value":5.522352,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"anthropic/claude-sonnet-4.6","source":"epoch","metric":"epoch_deepswe_pass_at_4","value":0.566372,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"anthropic/claude-sonnet-4.6","source":"epoch","metric":"epoch_deepswe_output_tokens","value":76160.312639,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"anthropic/claude-sonnet-4.6","source":"epoch","metric":"epoch_deepswe_agent_steps","value":133.658537,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_deepswe","value":0.1172566371681416,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_deepswe_cost_usd","value":2.143405,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_deepswe_pass_at_4","value":0.283186,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_deepswe_output_tokens","value":28368.884444,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_deepswe_agent_steps","value":75.564444,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_deepswe","value":0.7364864864864865,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_deepswe_cost_usd","value":11.837583,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_deepswe_pass_at_4","value":0.884956,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_deepswe_output_tokens","value":117565.693694,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_deepswe_agent_steps","value":99.042793,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_deepswe","value":0.6851441241685144,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_deepswe_cost_usd","value":4.654682,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_deepswe_pass_at_4","value":0.893805,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_deepswe_output_tokens","value":81499.842572,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_deepswe_agent_steps","value":97.587583,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"x-ai/grok-4.5","source":"epoch","metric":"epoch_deepswe","value":0.5376106194690266,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"x-ai/grok-4.5","source":"epoch","metric":"epoch_deepswe_cost_usd","value":2.415748,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"x-ai/grok-4.5","source":"epoch","metric":"epoch_deepswe_pass_at_4","value":0.778761,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"x-ai/grok-4.5","source":"epoch","metric":"epoch_deepswe_output_tokens","value":35525.331858,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"x-ai/grok-4.5","source":"epoch","metric":"epoch_deepswe_agent_steps","value":61.331858,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"google/gemini-3.6-flash","source":"epoch","metric":"epoch_deepswe","value":0.4668141592920354,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"google/gemini-3.6-flash","source":"epoch","metric":"epoch_deepswe_cost_usd","value":4.419013,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"google/gemini-3.6-flash","source":"epoch","metric":"epoch_deepswe_pass_at_4","value":0.752212,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"google/gemini-3.6-flash","source":"epoch","metric":"epoch_deepswe_output_tokens","value":95844.862222,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"google/gemini-3.6-flash","source":"epoch","metric":"epoch_deepswe_agent_steps","value":116.733333,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"google/gemini-3.5-flash","source":"epoch","metric":"epoch_deepswe","value":0.37389380530973454,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"google/gemini-3.5-flash","source":"epoch","metric":"epoch_deepswe_cost_usd","value":7.341824,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"google/gemini-3.5-flash","source":"epoch","metric":"epoch_deepswe_pass_at_4","value":0.663717,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"google/gemini-3.5-flash","source":"epoch","metric":"epoch_deepswe_output_tokens","value":275777.50885,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"google/gemini-3.5-flash","source":"epoch","metric":"epoch_deepswe_agent_steps","value":85.716814,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_deepswe","value":0.6747787610619469,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_deepswe_cost_usd","value":3.448984,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_deepswe_pass_at_4","value":0.840708,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_deepswe_output_tokens","value":49763.997788,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_deepswe_agent_steps","value":70.289823,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"qwen/qwen3.8-max-0902","source":"epoch","metric":"epoch_deepswe","value":0.5746102449888641,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"qwen/qwen3.8-max-0902","source":"epoch","metric":"epoch_deepswe_cost_usd","value":3.729065,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"qwen/qwen3.8-max-0902","source":"epoch","metric":"epoch_deepswe_pass_at_4","value":0.831858,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"qwen/qwen3.8-max-0902","source":"epoch","metric":"epoch_deepswe_output_tokens","value":95075.182628,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"qwen/qwen3.8-max-0902","source":"epoch","metric":"epoch_deepswe_agent_steps","value":111.33853,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"google/gemini-3.7-flash","source":"epoch","metric":"epoch_deepswe","value":0.6548672566371682,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"google/gemini-3.7-flash","source":"epoch","metric":"epoch_deepswe_cost_usd","value":2.025135,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"google/gemini-3.7-flash","source":"epoch","metric":"epoch_deepswe_pass_at_4","value":0.831858,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"google/gemini-3.7-flash","source":"epoch","metric":"epoch_deepswe_output_tokens","value":93990.85177,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"google/gemini-3.7-flash","source":"epoch","metric":"epoch_deepswe_agent_steps","value":117.369469,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"z-ai/glm-5.3","source":"epoch","metric":"epoch_deepswe","value":0.6895787139689579,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"z-ai/glm-5.3","source":"epoch","metric":"epoch_deepswe_cost_usd","value":3.993358,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"z-ai/glm-5.3","source":"epoch","metric":"epoch_deepswe_pass_at_4","value":0.876106,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"z-ai/glm-5.3","source":"epoch","metric":"epoch_deepswe_output_tokens","value":80435.609756,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"z-ai/glm-5.3","source":"epoch","metric":"epoch_deepswe_agent_steps","value":124.472284,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"meta/muse-spark-1.2","source":"epoch","metric":"epoch_deepswe","value":0.5486725663716814,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"meta/muse-spark-1.2","source":"epoch","metric":"epoch_deepswe_cost_usd","value":3.695505,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"meta/muse-spark-1.2","source":"epoch","metric":"epoch_deepswe_pass_at_4","value":0.814159,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"meta/muse-spark-1.2","source":"epoch","metric":"epoch_deepswe_output_tokens","value":99226.380531,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"meta/muse-spark-1.2","source":"epoch","metric":"epoch_deepswe_agent_steps","value":100.75885,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_deepswe","value":0.738255033557047,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_deepswe_cost_usd","value":2.362349,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_deepswe_pass_at_4","value":0.858407,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_deepswe_output_tokens","value":143242.66443,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_deepswe_agent_steps","value":166.313199,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"z-ai/glm-5.3-flash","source":"epoch","metric":"epoch_deepswe","value":0.6339285714285714,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"z-ai/glm-5.3-flash","source":"epoch","metric":"epoch_deepswe_cost_usd","value":0.481964,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"z-ai/glm-5.3-flash","source":"epoch","metric":"epoch_deepswe_pass_at_4","value":0.849558,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"z-ai/glm-5.3-flash","source":"epoch","metric":"epoch_deepswe_output_tokens","value":72829.770089,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"z-ai/glm-5.3-flash","source":"epoch","metric":"epoch_deepswe_agent_steps","value":122.890625,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_deepswe","value":0.7411504424778761,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_deepswe_cost_usd","value":4.429117,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_deepswe_pass_at_4","value":0.80531,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_deepswe_output_tokens","value":29557.327434,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_deepswe_agent_steps","value":28.754425,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://deepswe.datacurve.ai/"},{"modelId":"anthropic/claude-opus-5.5","source":"epoch","metric":"epoch_frontiercode","value":0.5464,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_frontiercode","value":0.5348,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_frontiercode","value":0.5338,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_frontiercode","value":0.5326,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"anthropic/claude-sonnet-5.5","source":"epoch","metric":"epoch_frontiercode","value":0.5209,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"anthropic/claude-fable-5.1","source":"epoch","metric":"epoch_frontiercode","value":0.5091,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"openai/gpt-6.1-sol","source":"epoch","metric":"epoch_frontiercode","value":0.5023,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"openai/gpt-6-sol","source":"epoch","metric":"epoch_frontiercode","value":0.4927,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_frontiercode","value":0.4801000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"x-ai/grok-4.7","source":"epoch","metric":"epoch_frontiercode","value":0.4759,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"google/gemini-4-argon","source":"epoch","metric":"epoch_frontiercode","value":0.4755,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_frontiercode","value":0.47490000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_frontiercode","value":0.465,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"anthropic/claude-haiku-5.5","source":"epoch","metric":"epoch_frontiercode","value":0.4636,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_frontiercode","value":0.44170000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"epoch","metric":"epoch_frontiercode","value":0.4387,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"google/gemini-3.7-flash","source":"epoch","metric":"epoch_frontiercode","value":0.43590000000000007,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_frontiercode","value":0.42960000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"anthropic/claude-sonnet-5","source":"epoch","metric":"epoch_frontiercode","value":0.42730000000000007,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"x-ai/grok-4.5","source":"epoch","metric":"epoch_frontiercode","value":0.4244,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"openai/gpt-6-luna","source":"epoch","metric":"epoch_frontiercode","value":0.4242,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_frontiercode","value":0.4131,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_frontiercode","value":0.4119,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"z-ai/glm-5.3","source":"epoch","metric":"epoch_frontiercode","value":0.40140000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_frontiercode","value":0.3981,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"mistralai/mistral-large-4-0","source":"epoch","metric":"epoch_frontiercode","value":0.3943,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"anthropic/claude-opus-4.7","source":"epoch","metric":"epoch_frontiercode","value":0.3854,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"google/gemini-3.6-flash","source":"epoch","metric":"epoch_frontiercode","value":0.3437,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"z-ai/glm-5.3-flash","source":"epoch","metric":"epoch_frontiercode","value":0.3183,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"moonshotai/kimi-k2.7-code","source":"epoch","metric":"epoch_frontiercode","value":0.3006,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"epoch","metric":"epoch_frontiercode","value":0.2855,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"openai/gpt-5.4-mini","source":"epoch","metric":"epoch_frontiercode","value":0.2704,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"anthropic/claude-opus-4.6","source":"epoch","metric":"epoch_frontiercode","value":0.2664,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_frontiercode","value":0.245,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"anthropic/claude-sonnet-4.6","source":"epoch","metric":"epoch_frontiercode","value":0.24310000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"epoch","metric":"epoch_frontiercode","value":0.188,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"deepseek/deepseek-v4-pro","source":"epoch","metric":"epoch_frontiercode","value":0.1764,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"minimax/minimax-m3","source":"epoch","metric":"epoch_frontiercode","value":0.147,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"thinkingmachines/inkling","source":"epoch","metric":"epoch_frontiercode","value":0.14,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"epoch","metric":"epoch_frontiercode","value":0.1361,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"qwen/qwen3.7-plus","source":"epoch","metric":"epoch_frontiercode","value":0.102,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cognition.com/frontiercode"},{"modelId":"anthropic/claude-fable-5.1","source":"epoch","metric":"epoch_frontierswe","value":0.5629078999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-fable-5.1","source":"epoch","metric":"epoch_frontierswe_cost_usd","value":138.55,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-fable-5.1","source":"epoch","metric":"epoch_frontierswe_best_of_5","value":0.6665,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-fable-5.1","source":"epoch","metric":"epoch_frontierswe_hours","value":11.62,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-fable-5.1","source":"epoch","metric":"epoch_frontierswe_implementation","value":0.7322,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-fable-5.1","source":"epoch","metric":"epoch_frontierswe_performance","value":0.4314,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-fable-5.1","source":"epoch","metric":"epoch_frontierswe_research","value":0.5135,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_frontierswe","value":0.3220246705882353,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_frontierswe_cost_usd","value":179.64,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_frontierswe_best_of_5","value":0.4417,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_frontierswe_hours","value":8.6,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_frontierswe_implementation","value":0.4039,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_frontierswe_performance","value":0.2201,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_frontierswe_research","value":0.282,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"z-ai/glm-5.3","source":"epoch","metric":"epoch_frontierswe","value":0.3018186411764705,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"z-ai/glm-5.3","source":"epoch","metric":"epoch_frontierswe_cost_usd","value":97.22,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"z-ai/glm-5.3","source":"epoch","metric":"epoch_frontierswe_best_of_5","value":0.4064,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"z-ai/glm-5.3","source":"epoch","metric":"epoch_frontierswe_hours","value":17.04,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"z-ai/glm-5.3","source":"epoch","metric":"epoch_frontierswe_implementation","value":0.3465,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"z-ai/glm-5.3","source":"epoch","metric":"epoch_frontierswe_performance","value":0.2056,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"z-ai/glm-5.3","source":"epoch","metric":"epoch_frontierswe_research","value":0.2556,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_frontierswe","value":0.25865032058823534,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_frontierswe_cost_usd","value":109.71,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_frontierswe_best_of_5","value":0.3755,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_frontierswe_hours","value":18.4,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_frontierswe_implementation","value":0.2989,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_frontierswe_performance","value":0.1882,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_frontierswe_research","value":0.2105,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_frontierswe","value":0.25286195882352946,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_frontierswe_cost_usd","value":243.43,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_frontierswe_best_of_5","value":0.3729,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_frontierswe_hours","value":13.8,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_frontierswe_implementation","value":0.2457,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_frontierswe_performance","value":0.1638,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_frontierswe_research","value":0.2521,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"google/gemini-3.7-flash","source":"epoch","metric":"epoch_frontierswe","value":0.20260590588235297,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"google/gemini-3.7-flash","source":"epoch","metric":"epoch_frontierswe_cost_usd","value":34.14,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"google/gemini-3.7-flash","source":"epoch","metric":"epoch_frontierswe_best_of_5","value":0.3123,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"google/gemini-3.7-flash","source":"epoch","metric":"epoch_frontierswe_hours","value":7.87,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"google/gemini-3.7-flash","source":"epoch","metric":"epoch_frontierswe_implementation","value":0.2485,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"google/gemini-3.7-flash","source":"epoch","metric":"epoch_frontierswe_performance","value":0.1502,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"google/gemini-3.7-flash","source":"epoch","metric":"epoch_frontierswe_research","value":0.1431,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"qwen/qwen3.8-max-0902","source":"epoch","metric":"epoch_frontierswe","value":0.17809649411764705,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"qwen/qwen3.8-max-0902","source":"epoch","metric":"epoch_frontierswe_cost_usd","value":51.27,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"qwen/qwen3.8-max-0902","source":"epoch","metric":"epoch_frontierswe_best_of_5","value":0.2678,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"qwen/qwen3.8-max-0902","source":"epoch","metric":"epoch_frontierswe_hours","value":19.36,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"qwen/qwen3.8-max-0902","source":"epoch","metric":"epoch_frontierswe_implementation","value":0.1384,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"qwen/qwen3.8-max-0902","source":"epoch","metric":"epoch_frontierswe_performance","value":0.1616,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"qwen/qwen3.8-max-0902","source":"epoch","metric":"epoch_frontierswe_research","value":0.1603,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"meta/muse-spark-1.2","source":"epoch","metric":"epoch_frontierswe","value":0.11970256470588238,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"meta/muse-spark-1.2","source":"epoch","metric":"epoch_frontierswe_cost_usd","value":27.81,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"meta/muse-spark-1.2","source":"epoch","metric":"epoch_frontierswe_best_of_5","value":0.1836,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"meta/muse-spark-1.2","source":"epoch","metric":"epoch_frontierswe_hours","value":4.59,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"meta/muse-spark-1.2","source":"epoch","metric":"epoch_frontierswe_implementation","value":0.0265,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"meta/muse-spark-1.2","source":"epoch","metric":"epoch_frontierswe_performance","value":0.1145,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"meta/muse-spark-1.2","source":"epoch","metric":"epoch_frontierswe_research","value":0.1468,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"thinkingmachines/inkling","source":"epoch","metric":"epoch_frontierswe","value":0.04118886470588236,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"thinkingmachines/inkling","source":"epoch","metric":"epoch_frontierswe_cost_usd","value":9.15,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"thinkingmachines/inkling","source":"epoch","metric":"epoch_frontierswe_best_of_5","value":0.1079,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"thinkingmachines/inkling","source":"epoch","metric":"epoch_frontierswe_hours","value":1.16,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"thinkingmachines/inkling","source":"epoch","metric":"epoch_frontierswe_implementation","value":0.004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"thinkingmachines/inkling","source":"epoch","metric":"epoch_frontierswe_performance","value":0.0393,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"thinkingmachines/inkling","source":"epoch","metric":"epoch_frontierswe_research","value":0.0542,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_frontierswe","value":0.6550757455882352,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_frontierswe_cost_usd","value":1029.65,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_frontierswe_best_of_5","value":0.73,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_frontierswe_hours","value":12.1,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_frontierswe_implementation","value":0.8695,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_frontierswe_performance","value":0.4831,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_frontierswe_research","value":0.5911,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_frontierswe","value":0.5201176764705882,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_frontierswe_cost_usd","value":196.71,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_frontierswe_best_of_5","value":0.6065,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_frontierswe_hours","value":16.07,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_frontierswe_implementation","value":0.7053,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_frontierswe_performance","value":0.3779,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_frontierswe_research","value":0.4249,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_frontierswe","value":0.4696449352941177,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_frontierswe_cost_usd","value":301.28,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_frontierswe_best_of_5","value":0.6177,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_frontierswe_hours","value":15.82,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_frontierswe_implementation","value":0.6369,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_frontierswe_performance","value":0.3369,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_frontierswe_research","value":0.4045,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_frontierswe","value":0.19626902941176463,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_frontierswe_cost_usd","value":38.75,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_frontierswe_best_of_5","value":0.3164,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_frontierswe_hours","value":7.18,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_frontierswe_implementation","value":0.2304,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_frontierswe_performance","value":0.1488,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_frontierswe_research","value":0.1647,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-opus-5.5","source":"epoch","metric":"epoch_frontierswe","value":0.623309882352941,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-opus-5.5","source":"epoch","metric":"epoch_frontierswe_cost_usd","value":98.87,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-opus-5.5","source":"epoch","metric":"epoch_frontierswe_best_of_5","value":0.7152,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-opus-5.5","source":"epoch","metric":"epoch_frontierswe_hours","value":14.25,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-opus-5.5","source":"epoch","metric":"epoch_frontierswe_implementation","value":0.8039,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-opus-5.5","source":"epoch","metric":"epoch_frontierswe_performance","value":0.4529,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-opus-5.5","source":"epoch","metric":"epoch_frontierswe_research","value":0.5733,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"x-ai/grok-4.7","source":"epoch","metric":"epoch_frontierswe","value":0.2950476117647059,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"x-ai/grok-4.7","source":"epoch","metric":"epoch_frontierswe_cost_usd","value":318.77,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"x-ai/grok-4.7","source":"epoch","metric":"epoch_frontierswe_best_of_5","value":0.4106,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"x-ai/grok-4.7","source":"epoch","metric":"epoch_frontierswe_hours","value":12.06,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"x-ai/grok-4.7","source":"epoch","metric":"epoch_frontierswe_implementation","value":0.3639,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"x-ai/grok-4.7","source":"epoch","metric":"epoch_frontierswe_performance","value":0.1822,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"x-ai/grok-4.7","source":"epoch","metric":"epoch_frontierswe_research","value":0.2376,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-sonnet-5.5","source":"epoch","metric":"epoch_frontierswe","value":0.618892994117647,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-sonnet-5.5","source":"epoch","metric":"epoch_frontierswe_cost_usd","value":110.45,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-sonnet-5.5","source":"epoch","metric":"epoch_frontierswe_best_of_5","value":0.7169,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-sonnet-5.5","source":"epoch","metric":"epoch_frontierswe_hours","value":16.01,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-sonnet-5.5","source":"epoch","metric":"epoch_frontierswe_implementation","value":0.811,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-sonnet-5.5","source":"epoch","metric":"epoch_frontierswe_performance","value":0.4806,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-sonnet-5.5","source":"epoch","metric":"epoch_frontierswe_research","value":0.5452,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"google/gemini-4-argon","source":"epoch","metric":"epoch_frontierswe","value":0.5496118588235293,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"google/gemini-4-argon","source":"epoch","metric":"epoch_frontierswe_cost_usd","value":129.36,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"google/gemini-4-argon","source":"epoch","metric":"epoch_frontierswe_best_of_5","value":0.643,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"google/gemini-4-argon","source":"epoch","metric":"epoch_frontierswe_hours","value":10.56,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"google/gemini-4-argon","source":"epoch","metric":"epoch_frontierswe_implementation","value":0.7446,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"google/gemini-4-argon","source":"epoch","metric":"epoch_frontierswe_performance","value":0.3504,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"google/gemini-4-argon","source":"epoch","metric":"epoch_frontierswe_research","value":0.4767,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"z-ai/glm-5.3-flash","source":"epoch","metric":"epoch_frontierswe","value":0.18125205882352943,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"z-ai/glm-5.3-flash","source":"epoch","metric":"epoch_frontierswe_cost_usd","value":11.03,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"z-ai/glm-5.3-flash","source":"epoch","metric":"epoch_frontierswe_best_of_5","value":0.2845,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"z-ai/glm-5.3-flash","source":"epoch","metric":"epoch_frontierswe_hours","value":16.39,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"z-ai/glm-5.3-flash","source":"epoch","metric":"epoch_frontierswe_implementation","value":0.195,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"z-ai/glm-5.3-flash","source":"epoch","metric":"epoch_frontierswe_performance","value":0.1584,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"z-ai/glm-5.3-flash","source":"epoch","metric":"epoch_frontierswe_research","value":0.1329,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-haiku-5.5","source":"epoch","metric":"epoch_frontierswe","value":0.4376868294117648,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-haiku-5.5","source":"epoch","metric":"epoch_frontierswe_cost_usd","value":20.55,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-haiku-5.5","source":"epoch","metric":"epoch_frontierswe_best_of_5","value":0.5275,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-haiku-5.5","source":"epoch","metric":"epoch_frontierswe_hours","value":12.42,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-haiku-5.5","source":"epoch","metric":"epoch_frontierswe_implementation","value":0.5432,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-haiku-5.5","source":"epoch","metric":"epoch_frontierswe_performance","value":0.2872,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-haiku-5.5","source":"epoch","metric":"epoch_frontierswe_research","value":0.3746,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"meta/muse-spark-1.3","source":"epoch","metric":"epoch_frontierswe","value":0.2580214823529412,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"meta/muse-spark-1.3","source":"epoch","metric":"epoch_frontierswe_cost_usd","value":243.34,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"meta/muse-spark-1.3","source":"epoch","metric":"epoch_frontierswe_best_of_5","value":0.4092,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"meta/muse-spark-1.3","source":"epoch","metric":"epoch_frontierswe_hours","value":16.97,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"meta/muse-spark-1.3","source":"epoch","metric":"epoch_frontierswe_implementation","value":0.2878,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"meta/muse-spark-1.3","source":"epoch","metric":"epoch_frontierswe_performance","value":0.1705,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"meta/muse-spark-1.3","source":"epoch","metric":"epoch_frontierswe_research","value":0.2212,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.frontierswe.com/"},{"modelId":"anthropic/claude-fable-5.1","source":"epoch","metric":"epoch_gso","value":0.8824,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://gso-bench.github.io/index.html"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_gso","value":0.7941,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://gso-bench.github.io/index.html"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_gso","value":0.7843000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://gso-bench.github.io/index.html"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_gso","value":0.7647,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://gso-bench.github.io/index.html"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_gso","value":0.4706,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://gso-bench.github.io/index.html"},{"modelId":"anthropic/claude-opus-4.7","source":"epoch","metric":"epoch_gso","value":0.4412,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://gso-bench.github.io/index.html"},{"modelId":"anthropic/claude-opus-4.6","source":"epoch","metric":"epoch_gso","value":0.412,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_gso","value":0.402,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://gso-bench.github.io/index.html"},{"modelId":"anthropic/claude-sonnet-5","source":"epoch","metric":"epoch_gso","value":0.3725,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://gso-bench.github.io/index.html"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_gso","value":0.31370000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://gso-bench.github.io/index.html"},{"modelId":"openai/gpt-5.2","source":"epoch","metric":"epoch_gso","value":0.2745,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://gso-bench.github.io/index.html"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_gso","value":0.265,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://gso-bench.github.io/leaderboard.html"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_gso","value":0.2255,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://gso-bench.github.io/index.html"},{"modelId":"anthropic/claude-sonnet-4.5","source":"epoch","metric":"epoch_gso","value":0.1471,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.1","source":"epoch","metric":"epoch_gso","value":0.1373,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://gso-bench.github.io/index.html"},{"modelId":"google/gemini-3-flash-preview","source":"epoch","metric":"epoch_gso","value":0.098,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://gso-bench.github.io/index.html"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_gso","value":0.088,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://gso-bench.github.io/leaderboard.html"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_gso","value":0.06860000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://gso-bench.github.io/leaderboard.html"},{"modelId":"moonshotai/kimi-k2","source":"epoch","metric":"epoch_gso","value":0.049,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://gso-bench.github.io/leaderboard.html"},{"modelId":"qwen/qwen3-coder","source":"epoch","metric":"epoch_gso","value":0.049,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://gso-bench.github.io/leaderboard.html"},{"modelId":"google/gemini-2.5-pro","source":"epoch","metric":"epoch_gso","value":0.0392,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://gso-bench.github.io/leaderboard.html"},{"modelId":"google/gemini-2.5-pro-preview","source":"epoch","metric":"epoch_gso","value":0.0392,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_gso","value":0.036,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://gso-bench.github.io/leaderboard.html"},{"modelId":"z-ai/glm-4.5-air","source":"epoch","metric":"epoch_gso","value":0.0294,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o3-mini","source":"epoch","metric":"epoch_gso","value":0.013000000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4o-2024-11-20","source":"epoch","metric":"epoch_gso","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://gso-bench.github.io/leaderboard.html"},{"modelId":"openai/gpt-6-astra-pro","source":"epoch","metric":"epoch_weirdml","value":0.9357,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-6-astra-pro","source":"epoch","metric":"epoch_weirdml_cost_usd","value":29.305756,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-6-astra-pro","source":"epoch","metric":"epoch_weirdml_code_lines","value":520.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_weirdml","value":0.9328000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_weirdml_cost_usd","value":7.748508,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_weirdml_code_lines","value":485,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"anthropic/claude-fable-5.1","source":"epoch","metric":"epoch_weirdml","value":0.929,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"anthropic/claude-fable-5.1","source":"epoch","metric":"epoch_weirdml_cost_usd","value":11.686584,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"anthropic/claude-fable-5.1","source":"epoch","metric":"epoch_weirdml_code_lines","value":251,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_weirdml","value":0.9194,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_weirdml_cost_usd","value":8.42441,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_weirdml_code_lines","value":217.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_weirdml","value":0.9178000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_weirdml_cost_usd","value":4.741955,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_weirdml_code_lines","value":244.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5.6-sol-pro","source":"epoch","metric":"epoch_weirdml","value":0.8943000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5.6-sol-pro","source":"epoch","metric":"epoch_weirdml_cost_usd","value":3.870742,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5.6-sol-pro","source":"epoch","metric":"epoch_weirdml_code_lines","value":673.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_weirdml","value":0.8876000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_weirdml_cost_usd","value":1.254799,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_weirdml_code_lines","value":567,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_weirdml","value":0.8491,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_weirdml_cost_usd","value":2.568345,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_weirdml_code_lines","value":517,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_weirdml","value":0.8481000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.507268,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_weirdml_code_lines","value":438.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_weirdml","value":0.8289,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_weirdml_cost_usd","value":2.349812,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_weirdml_code_lines","value":129,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_weirdml","value":0.8257,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_weirdml_cost_usd","value":2.053659,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_weirdml_code_lines","value":244,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5.3-codex","source":"epoch","metric":"epoch_weirdml","value":0.793,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.3-codex","source":"epoch","metric":"epoch_weirdml_cost_usd","value":2.35,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.3-codex","source":"epoch","metric":"epoch_weirdml_code_lines","value":558,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_weirdml","value":0.7827,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.311906,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_weirdml_code_lines","value":177,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"anthropic/claude-opus-4.6","source":"epoch","metric":"epoch_weirdml","value":0.7795000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"anthropic/claude-opus-4.6","source":"epoch","metric":"epoch_weirdml_cost_usd","value":5.779371,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"anthropic/claude-opus-4.6","source":"epoch","metric":"epoch_weirdml_code_lines","value":169,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_weirdml","value":0.777,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_weirdml_cost_usd","value":5.71994,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_weirdml_code_lines","value":967.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"anthropic/claude-opus-4.7","source":"epoch","metric":"epoch_weirdml","value":0.7644,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"anthropic/claude-opus-4.7","source":"epoch","metric":"epoch_weirdml_cost_usd","value":1.820711,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"anthropic/claude-opus-4.7","source":"epoch","metric":"epoch_weirdml_code_lines","value":147,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"z-ai/glm-5.3","source":"epoch","metric":"epoch_weirdml","value":0.7540000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"z-ai/glm-5.3","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.535145,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"z-ai/glm-5.3","source":"epoch","metric":"epoch_weirdml_code_lines","value":243.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5.2","source":"epoch","metric":"epoch_weirdml","value":0.7219,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5.2","source":"epoch","metric":"epoch_weirdml_cost_usd","value":2.047381,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5.2","source":"epoch","metric":"epoch_weirdml_code_lines","value":393.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_weirdml","value":0.7206999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_weirdml_cost_usd","value":1.360187,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_weirdml_code_lines","value":212,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_weirdml","value":0.7012,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.507287,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_weirdml_code_lines","value":200,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"anthropic/claude-sonnet-5","source":"epoch","metric":"epoch_weirdml","value":0.6878000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"anthropic/claude-sonnet-5","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.895463,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"anthropic/claude-sonnet-5","source":"epoch","metric":"epoch_weirdml_code_lines","value":233,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_weirdml","value":0.6729,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.334832,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_weirdml_code_lines","value":205,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"epoch","metric":"epoch_weirdml","value":0.6622,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.191032,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"epoch","metric":"epoch_weirdml_code_lines","value":318,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"anthropic/claude-sonnet-4.6","source":"epoch","metric":"epoch_weirdml","value":0.6607,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-4.6","source":"epoch","metric":"epoch_weirdml_cost_usd","value":2.85935,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-4.6","source":"epoch","metric":"epoch_weirdml_code_lines","value":178,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_weirdml","value":0.6374000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.738304,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_weirdml_code_lines","value":173,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"epoch","metric":"epoch_weirdml","value":0.6296,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.028578,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"epoch","metric":"epoch_weirdml_code_lines","value":274,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"google/gemini-3.5-flash","source":"epoch","metric":"epoch_weirdml","value":0.6264000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"google/gemini-3.5-flash","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.756041,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"google/gemini-3.5-flash","source":"epoch","metric":"epoch_weirdml_code_lines","value":285.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"google/gemini-3-flash-preview","source":"epoch","metric":"epoch_weirdml","value":0.616,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"google/gemini-3-flash-preview","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.221588,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"google/gemini-3-flash-preview","source":"epoch","metric":"epoch_weirdml_code_lines","value":149,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_weirdml","value":0.6086,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.19999,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_weirdml_code_lines","value":289,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5.1","source":"epoch","metric":"epoch_weirdml","value":0.6077,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5.1","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.691335,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5.1","source":"epoch","metric":"epoch_weirdml_code_lines","value":311,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_weirdml","value":0.6070000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.59318,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_weirdml_code_lines","value":328,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5-pro","source":"epoch","metric":"epoch_weirdml","value":0.6039,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5-pro","source":"epoch","metric":"epoch_weirdml_cost_usd","value":7.647644,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5-pro","source":"epoch","metric":"epoch_weirdml_code_lines","value":369,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5.4-mini","source":"epoch","metric":"epoch_weirdml","value":0.603,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5.4-mini","source":"epoch","metric":"epoch_weirdml_cost_usd","value":1.291017,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5.4-mini","source":"epoch","metric":"epoch_weirdml_code_lines","value":503,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"meta/muse-spark-1.2","source":"epoch","metric":"epoch_weirdml","value":0.603,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"meta/muse-spark-1.2","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.380109,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"meta/muse-spark-1.2","source":"epoch","metric":"epoch_weirdml_code_lines","value":272,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/o3-pro","source":"epoch","metric":"epoch_weirdml","value":0.5821000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/o3-pro","source":"epoch","metric":"epoch_weirdml_cost_usd","value":2.540383,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/o3-pro","source":"epoch","metric":"epoch_weirdml_code_lines","value":148,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5.4-pro","source":"epoch","metric":"epoch_weirdml","value":0.5744,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5.4-pro","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.267909,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5.4-pro","source":"epoch","metric":"epoch_weirdml_code_lines","value":292,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"z-ai/glm-5.1","source":"epoch","metric":"epoch_weirdml","value":0.5710000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"z-ai/glm-5.1","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.317512,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"z-ai/glm-5.1","source":"epoch","metric":"epoch_weirdml_code_lines","value":178,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"google/gemini-3.6-flash","source":"epoch","metric":"epoch_weirdml","value":0.561,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"google/gemini-3.6-flash","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.622712,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"google/gemini-3.6-flash","source":"epoch","metric":"epoch_weirdml_code_lines","value":345.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"moonshotai/kimi-k2.6","source":"epoch","metric":"epoch_weirdml","value":0.5586,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"moonshotai/kimi-k2.6","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.350354,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"moonshotai/kimi-k2.6","source":"epoch","metric":"epoch_weirdml_code_lines","value":205,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"moonshotai/kimi-k2.7-code","source":"epoch","metric":"epoch_weirdml","value":0.5412,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"moonshotai/kimi-k2.7-code","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.231634,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"moonshotai/kimi-k2.7-code","source":"epoch","metric":"epoch_weirdml_code_lines","value":230,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"google/gemini-2.5-pro","source":"epoch","metric":"epoch_weirdml","value":0.5403,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"google/gemini-2.5-pro","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.40966,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"google/gemini-2.5-pro","source":"epoch","metric":"epoch_weirdml_code_lines","value":199,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_weirdml","value":0.5267000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.109767,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_weirdml_code_lines","value":296,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_weirdml","value":0.5256000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.195685,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_weirdml_code_lines","value":122,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_weirdml","value":0.5242,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.226067,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_weirdml_code_lines","value":134,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"x-ai/grok-4.20","source":"epoch","metric":"epoch_weirdml","value":0.5226,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"x-ai/grok-4.20","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.126283,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"x-ai/grok-4.20","source":"epoch","metric":"epoch_weirdml_code_lines","value":117,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"google/gemma-4-31b-it","source":"epoch","metric":"epoch_weirdml","value":0.5226,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"google/gemma-4-31b-it","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.013265,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"google/gemma-4-31b-it","source":"epoch","metric":"epoch_weirdml_code_lines","value":126,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"google/gemini-3.1-flash-lite","source":"epoch","metric":"epoch_weirdml","value":0.5219,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.1-flash-lite","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.066424,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.1-flash-lite","source":"epoch","metric":"epoch_weirdml_code_lines","value":107,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.3","source":"epoch","metric":"epoch_weirdml","value":0.4989,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"x-ai/grok-4.3","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.09032,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"x-ai/grok-4.3","source":"epoch","metric":"epoch_weirdml_code_lines","value":141,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5.4-nano","source":"epoch","metric":"epoch_weirdml","value":0.49229999999999996,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5.4-nano","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.047747,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5.4-nano","source":"epoch","metric":"epoch_weirdml_code_lines","value":279,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"deepseek/deepseek-v4-pro","source":"epoch","metric":"epoch_weirdml","value":0.489,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"deepseek/deepseek-v4-pro","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.3403,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"deepseek/deepseek-v4-pro","source":"epoch","metric":"epoch_weirdml_code_lines","value":272,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-oss-120b","source":"epoch","metric":"epoch_weirdml","value":0.4817,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-oss-120b","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.033483,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-oss-120b","source":"epoch","metric":"epoch_weirdml_code_lines","value":255,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"z-ai/glm-5","source":"epoch","metric":"epoch_weirdml","value":0.4817,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.078745,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5","source":"epoch","metric":"epoch_weirdml_code_lines","value":161,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-4.5","source":"epoch","metric":"epoch_weirdml","value":0.4771,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"anthropic/claude-sonnet-4.5","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.334378,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"anthropic/claude-sonnet-4.5","source":"epoch","metric":"epoch_weirdml_code_lines","value":173,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"x-ai/grok-4.5","source":"epoch","metric":"epoch_weirdml","value":0.4643,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"x-ai/grok-4.5","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.080463,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"x-ai/grok-4.5","source":"epoch","metric":"epoch_weirdml_code_lines","value":86,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/o1","source":"epoch","metric":"epoch_weirdml","value":0.4608,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/o1","source":"epoch","metric":"epoch_weirdml_cost_usd","value":2.028669,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/o1","source":"epoch","metric":"epoch_weirdml_code_lines","value":152,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"anthropic/claude-opus-4.1","source":"epoch","metric":"epoch_weirdml","value":0.4586,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"anthropic/claude-opus-4.1","source":"epoch","metric":"epoch_weirdml_cost_usd","value":1.755553,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"anthropic/claude-opus-4.1","source":"epoch","metric":"epoch_weirdml_code_lines","value":241,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"deepseek/deepseek-v4-flash","source":"epoch","metric":"epoch_weirdml","value":0.45630000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"deepseek/deepseek-v4-flash","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.014616,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"deepseek/deepseek-v4-flash","source":"epoch","metric":"epoch_weirdml_code_lines","value":204,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"moonshotai/kimi-k2.5","source":"epoch","metric":"epoch_weirdml","value":0.456,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"moonshotai/kimi-k2.5","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.052612,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"moonshotai/kimi-k2.5","source":"epoch","metric":"epoch_weirdml_code_lines","value":166,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"anthropic/claude-haiku-4.5","source":"epoch","metric":"epoch_weirdml","value":0.454,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"anthropic/claude-haiku-4.5","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.089387,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"anthropic/claude-haiku-4.5","source":"epoch","metric":"epoch_weirdml_code_lines","value":174,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/o3-mini","source":"epoch","metric":"epoch_weirdml","value":0.43700000000000006,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/o3-mini","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.174467,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/o3-mini","source":"epoch","metric":"epoch_weirdml_code_lines","value":158,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"epoch","metric":"epoch_weirdml","value":0.43450000000000005,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.077202,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"epoch","metric":"epoch_weirdml_code_lines","value":232,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"inception/mercury-2","source":"epoch","metric":"epoch_weirdml","value":0.43200000000000005,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"inception/mercury-2","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.029776,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"inception/mercury-2","source":"epoch","metric":"epoch_weirdml_code_lines","value":201,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"moonshotai/kimi-k2-thinking","source":"epoch","metric":"epoch_weirdml","value":0.4279,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"moonshotai/kimi-k2-thinking","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.080938,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"moonshotai/kimi-k2-thinking","source":"epoch","metric":"epoch_weirdml_code_lines","value":195,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"deepseek/deepseek-r1-0528","source":"epoch","metric":"epoch_weirdml","value":0.41630000000000006,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"deepseek/deepseek-r1-0528","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.071068,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"deepseek/deepseek-r1-0528","source":"epoch","metric":"epoch_weirdml_code_lines","value":174,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"qwen/qwen3-coder","source":"epoch","metric":"epoch_weirdml","value":0.4117,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"qwen/qwen3-coder","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.072592,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"qwen/qwen3-coder","source":"epoch","metric":"epoch_weirdml_code_lines","value":174,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"epoch","metric":"epoch_weirdml","value":0.4104,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.019895,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"epoch","metric":"epoch_weirdml_code_lines","value":127,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-oss-20b","source":"epoch","metric":"epoch_weirdml","value":0.4093,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-oss-20b","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.0108,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-oss-20b","source":"epoch","metric":"epoch_weirdml_code_lines","value":166,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"z-ai/glm-4.5","source":"epoch","metric":"epoch_weirdml","value":0.4058,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"z-ai/glm-4.5","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.07348,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"z-ai/glm-4.5","source":"epoch","metric":"epoch_weirdml_code_lines","value":245.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"qwen/qwen3.5-27b","source":"epoch","metric":"epoch_weirdml","value":0.39530000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"qwen/qwen3.5-27b","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.040395,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"qwen/qwen3.5-27b","source":"epoch","metric":"epoch_weirdml_code_lines","value":171,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"epoch","metric":"epoch_weirdml","value":0.3948,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.017723,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"epoch","metric":"epoch_weirdml_code_lines","value":219,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"moonshotai/kimi-k2","source":"epoch","metric":"epoch_weirdml","value":0.3936,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"moonshotai/kimi-k2","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.0343,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"moonshotai/kimi-k2","source":"epoch","metric":"epoch_weirdml_code_lines","value":186,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-4.1","source":"epoch","metric":"epoch_weirdml","value":0.3904,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-4.1","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.09703,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-4.1","source":"epoch","metric":"epoch_weirdml_code_lines","value":138,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"google/gemini-3.5-flash-lite","source":"epoch","metric":"epoch_weirdml","value":0.39,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"google/gemini-3.5-flash-lite","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.046756,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"google/gemini-3.5-flash-lite","source":"epoch","metric":"epoch_weirdml_code_lines","value":130,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"epoch","metric":"epoch_weirdml","value":0.387,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.013407,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"epoch","metric":"epoch_weirdml_code_lines","value":144,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5-nano","source":"epoch","metric":"epoch_weirdml","value":0.38060000000000005,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5-nano","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.02622,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-5-nano","source":"epoch","metric":"epoch_weirdml_code_lines","value":191,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"epoch","metric":"epoch_weirdml","value":0.3801,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.012169,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"epoch","metric":"epoch_weirdml_code_lines","value":178,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-4.1-mini","source":"epoch","metric":"epoch_weirdml","value":0.3761,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-4.1-mini","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.016607,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-4.1-mini","source":"epoch","metric":"epoch_weirdml_code_lines","value":143,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"minimax/minimax-m2.7","source":"epoch","metric":"epoch_weirdml","value":0.36950000000000005,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"minimax/minimax-m2.7","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.034907,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"minimax/minimax-m2.7","source":"epoch","metric":"epoch_weirdml_code_lines","value":218,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"moonshotai/kimi-k2-0905","source":"epoch","metric":"epoch_weirdml","value":0.3668,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"moonshotai/kimi-k2-0905","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.04182,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"moonshotai/kimi-k2-0905","source":"epoch","metric":"epoch_weirdml_code_lines","value":211,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"epoch","metric":"epoch_weirdml","value":0.3608,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.013904,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"epoch","metric":"epoch_weirdml_code_lines","value":144,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"google/gemma-4-26b-a4b-it","source":"epoch","metric":"epoch_weirdml","value":0.3517,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"google/gemma-4-26b-a4b-it","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.020794,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"google/gemma-4-26b-a4b-it","source":"epoch","metric":"epoch_weirdml_code_lines","value":146,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"qwen/qwen3.6-35b-a3b","source":"epoch","metric":"epoch_weirdml","value":0.34490000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"qwen/qwen3.6-35b-a3b","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.059616,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"qwen/qwen3.6-35b-a3b","source":"epoch","metric":"epoch_weirdml_code_lines","value":147,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"qwen/qwen3-coder-next","source":"epoch","metric":"epoch_weirdml","value":0.344,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3-coder-next","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.03283,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3-coder-next","source":"epoch","metric":"epoch_weirdml_code_lines","value":201,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"thinkingmachines/inkling","source":"epoch","metric":"epoch_weirdml","value":0.3229,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"thinkingmachines/inkling","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.125543,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"thinkingmachines/inkling","source":"epoch","metric":"epoch_weirdml_code_lines","value":96,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"qwen/qwen3-30b-a3b","source":"epoch","metric":"epoch_weirdml","value":0.2975,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"qwen/qwen3-30b-a3b","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.008148,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"qwen/qwen3-30b-a3b","source":"epoch","metric":"epoch_weirdml_code_lines","value":103,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-4o-2024-11-20","source":"epoch","metric":"epoch_weirdml","value":0.25120000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-4o-2024-11-20","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.083556,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-4o-2024-11-20","source":"epoch","metric":"epoch_weirdml_code_lines","value":108,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"meta-llama/llama-4-maverick","source":"epoch","metric":"epoch_weirdml","value":0.2447,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"meta-llama/llama-4-maverick","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.006132,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"meta-llama/llama-4-maverick","source":"epoch","metric":"epoch_weirdml_code_lines","value":90,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-4.1-nano","source":"epoch","metric":"epoch_weirdml","value":0.1898,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-4.1-nano","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.002582,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-4.1-nano","source":"epoch","metric":"epoch_weirdml_code_lines","value":88,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"epoch","metric":"epoch_weirdml","value":0.1597,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.011328,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"epoch","metric":"epoch_weirdml_code_lines","value":101,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"epoch","metric":"epoch_weirdml","value":0.1444,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.001469,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"epoch","metric":"epoch_weirdml_code_lines","value":102,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"epoch","metric":"epoch_weirdml","value":0.1176,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.005261,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"epoch","metric":"epoch_weirdml_code_lines","value":85,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"epoch","metric":"epoch_weirdml","value":0.0897,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.003223,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"epoch","metric":"epoch_weirdml_code_lines","value":86,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"epoch","metric":"epoch_weirdml","value":0.0173,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"epoch","metric":"epoch_weirdml_cost_usd","value":0.00041,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"epoch","metric":"epoch_weirdml_code_lines","value":78,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://htihle.github.io/weirdml.html"},{"modelId":"anthropic/claude-opus-5.5","source":"epoch","metric":"epoch_mirrorcode","value":0.774,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-fable-5.1","source":"epoch","metric":"epoch_mirrorcode","value":0.733,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_mirrorcode","value":0.467,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.7","source":"epoch","metric":"epoch_mirrorcode","value":0.3111111111111111,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_mirrorcode","value":0.08888888888888888,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_mirrorcode","value":0.1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_mirrorcode","value":0.15555555555555556,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_mirrorcode","value":0.2,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_mirrorcode","value":0.638888888888889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-4-argon","source":"epoch","metric":"epoch_apex_agents","value":0.8240000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-4-argon","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.874,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-5.5","source":"epoch","metric":"epoch_apex_agents","value":0.755,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-5.5","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.837,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-5.5","source":"epoch","metric":"epoch_apex_agents","value":0.735,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-5.5","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.813,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-fable-5.1","source":"epoch","metric":"epoch_apex_agents","value":0.6859999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-fable-5.1","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.771,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.7-flash","source":"epoch","metric":"epoch_apex_agents","value":0.6779999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.7-flash","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.794,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_apex_agents","value":0.658,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.77,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_apex_agents","value":0.653,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.773,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_apex_agents","value":0.647,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.751,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_apex_agents","value":0.643,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.729,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_apex_agents","value":0.636,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.745,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.8-max-0902","source":"epoch","metric":"epoch_apex_agents","value":0.633,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.8-max-0902","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.743,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6.1-sol","source":"epoch","metric":"epoch_apex_agents","value":0.6,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6.1-sol","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.732,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta/muse-spark-1.3","source":"epoch","metric":"epoch_apex_agents","value":0.5860000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta/muse-spark-1.3","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.704,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_apex_agents","value":0.5820000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.718,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.3","source":"epoch","metric":"epoch_apex_agents","value":0.5660000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.3","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.662,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.5","source":"epoch","metric":"epoch_apex_agents","value":0.562,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.5","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.705,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-haiku-5.5","source":"epoch","metric":"epoch_apex_agents","value":0.561,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-haiku-5.5","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.683,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_apex_agents","value":0.551,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.703,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.7","source":"epoch","metric":"epoch_apex_agents","value":0.546,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.7","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.687,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-5","source":"epoch","metric":"epoch_apex_agents","value":0.545,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-5","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.674,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"epoch","metric":"epoch_apex_agents","value":0.544,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.653,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-sol","source":"epoch","metric":"epoch_apex_agents","value":0.543,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-sol","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.687,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.3-flash","source":"epoch","metric":"epoch_apex_agents","value":0.528,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.3-flash","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.668,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_apex_agents","value":0.524,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.682,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-sol-pro","source":"epoch","metric":"epoch_apex_agents","value":0.514,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-sol-pro","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.652,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.7","source":"epoch","metric":"epoch_apex_agents","value":0.49200000000000005,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.7","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.631,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_apex_agents","value":0.489,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.644,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_apex_agents","value":0.478,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.622,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.8-27b","source":"epoch","metric":"epoch_apex_agents","value":0.47500000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.8-27b","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.622,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"epoch","metric":"epoch_apex_agents","value":0.473,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.623,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.6-flash","source":"epoch","metric":"epoch_apex_agents","value":0.469,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.6-flash","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.634,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.6","source":"epoch","metric":"epoch_apex_agents","value":0.46299999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.6","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.618,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta/muse-spark-1.2","source":"epoch","metric":"epoch_apex_agents","value":0.454,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta/muse-spark-1.2","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.598,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_apex_agents","value":0.452,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.611,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-luna","source":"epoch","metric":"epoch_apex_agents","value":0.443,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-luna","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.59,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-4.6","source":"epoch","metric":"epoch_apex_agents","value":0.43,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-4.6","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.576,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_apex_agents","value":0.43,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.578,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.1","source":"epoch","metric":"epoch_apex_agents","value":0.409,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.1","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.568,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"epoch","metric":"epoch_apex_agents","value":0.395,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.505,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"minimax/minimax-m3","source":"epoch","metric":"epoch_apex_agents","value":0.37700000000000006,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"minimax/minimax-m3","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.535,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k2.7-code","source":"epoch","metric":"epoch_apex_agents","value":0.376,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k2.7-code","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.534,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_apex_agents","value":0.35100000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.522,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"thinkingmachines/inkling","source":"epoch","metric":"epoch_apex_agents","value":0.33799999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"thinkingmachines/inkling","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.488,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta/muse-spark-open","source":"epoch","metric":"epoch_apex_agents","value":0.334,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta/muse-spark-open","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.487,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta/muse-spark-1.1","source":"epoch","metric":"epoch_apex_agents","value":0.318,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta/muse-spark-1.1","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.462,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.5-flash-lite","source":"epoch","metric":"epoch_apex_agents","value":0.29300000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.5-flash-lite","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.461,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.5-flash","source":"epoch","metric":"epoch_apex_agents","value":0.275,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.5-flash","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.443,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"epoch","metric":"epoch_apex_agents","value":0.249,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.403,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"epoch","metric":"epoch_apex_agents","value":0.227,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.383,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v3.2","source":"epoch","metric":"epoch_apex_agents","value":0.21300000000000002,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v3.2","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.351,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-oss-120b","source":"epoch","metric":"epoch_apex_agents","value":0.044000000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-oss-120b","source":"epoch","metric":"epoch_apex_agents_mean_score","value":0.083,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.6","source":"epoch","metric":"epoch_metr_time_horizons","value":0.788644,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_metr_time_horizons","value":0.77035,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://metr.org/blog/2025-03-19-measuring-ai-ability-to-complete-long-tasks/"},{"modelId":"openai/gpt-5.2","source":"epoch","metric":"epoch_metr_time_horizons","value":0.752875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.3-codex","source":"epoch","metric":"epoch_metr_time_horizons","value":0.745439,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_metr_time_horizons","value":0.743443,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://metr.org/blog/2025-03-19-measuring-ai-ability-to-complete-long-tasks/"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_metr_time_horizons","value":0.74969,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://metr.org/blog/2025-03-19-measuring-ai-ability-to-complete-long-tasks/"},{"modelId":"openai/gpt-5.1-codex-max","source":"epoch","metric":"epoch_metr_time_horizons","value":0.708301,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://metr.org/blog/2025-03-19-measuring-ai-ability-to-complete-long-tasks/"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_metr_time_horizons","value":0.696053,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://metr.org/blog/2025-03-19-measuring-ai-ability-to-complete-long-tasks/"},{"modelId":"anthropic/claude-sonnet-4.5","source":"epoch","metric":"epoch_metr_time_horizons","value":0.673842,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://metr.org/blog/2025-03-19-measuring-ai-ability-to-complete-long-tasks/"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_metr_time_horizons","value":0.654376,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://metr.org/blog/2025-03-19-measuring-ai-ability-to-complete-long-tasks/"},{"modelId":"anthropic/claude-opus-4.1","source":"epoch","metric":"epoch_metr_time_horizons","value":0.668069,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://metr.org/blog/2025-03-19-measuring-ai-ability-to-complete-long-tasks/"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_metr_time_horizons","value":0.639269,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://metr.org/blog/2025-03-19-measuring-ai-ability-to-complete-long-tasks/"},{"modelId":"moonshotai/kimi-k2-thinking","source":"epoch","metric":"epoch_metr_time_horizons","value":0.591943,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://metr.org/blog/2025-03-19-measuring-ai-ability-to-complete-long-tasks/"},{"modelId":"openai/gpt-oss-120b","source":"epoch","metric":"epoch_metr_time_horizons","value":0.56634,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://metr.org/blog/2025-03-19-measuring-ai-ability-to-complete-long-tasks/"},{"modelId":"openai/o1","source":"epoch","metric":"epoch_metr_time_horizons","value":0.510512,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://metr.org/blog/2025-03-19-measuring-ai-ability-to-complete-long-tasks/"},{"modelId":"google/gemini-2.5-pro-preview","source":"epoch","metric":"epoch_metr_time_horizons","value":0.5544,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://metr.org/blog/2025-03-19-measuring-ai-ability-to-complete-long-tasks/"},{"modelId":"deepseek/deepseek-r1-0528","source":"epoch","metric":"epoch_metr_time_horizons","value":0.537826,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://metr.org/blog/2025-03-19-measuring-ai-ability-to-complete-long-tasks/"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"epoch","metric":"epoch_metr_time_horizons","value":0.495813,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://metr.org/blog/2025-03-19-measuring-ai-ability-to-complete-long-tasks/"},{"modelId":"openai/gpt-4o-2024-05-13","source":"epoch","metric":"epoch_metr_time_horizons","value":0.407636,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://metr.org/blog/2025-03-19-measuring-ai-ability-to-complete-long-tasks/"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"epoch","metric":"epoch_metr_time_horizons","value":0.357771,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://metr.org/blog/2025-03-19-measuring-ai-ability-to-complete-long-tasks/"},{"modelId":"openai/gpt-3.5-turbo-instruct","source":"epoch","metric":"epoch_metr_time_horizons","value":0.214611,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://metr.org/blog/2025-03-19-measuring-ai-ability-to-complete-long-tasks/"},{"modelId":"anthropic/claude-opus-5.5","source":"epoch","metric":"epoch_remote_labor_index","value":0.2125,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_remote_labor_index","value":0.20829999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-fable-5.1","source":"epoch","metric":"epoch_remote_labor_index","value":0.17920000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_remote_labor_index","value":0.161,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_remote_labor_index","value":0.0833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_remote_labor_index","value":0.0625,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_remote_labor_index","value":0.058300000000000005,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.7-flash","source":"epoch","metric":"epoch_remote_labor_index","value":0.05,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.6","source":"epoch","metric":"epoch_remote_labor_index","value":0.0417,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_remote_labor_index","value":0.0375,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.2","source":"epoch","metric":"epoch_remote_labor_index","value":0.025019999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-4.5","source":"epoch","metric":"epoch_remote_labor_index","value":0.020800000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_remote_labor_index","value":0.0167,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-2.5-pro-preview","source":"epoch","metric":"epoch_remote_labor_index","value":0.0083,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.2","source":"epoch","metric":"epoch_gdpval","value":0.49700000000000005,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_gdpval","value":0.455,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.1","source":"epoch","metric":"epoch_gdpval","value":0.436,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-4.5","source":"epoch","metric":"epoch_gdpval","value":0.425,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_gdpval","value":0.348,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_gdpval","value":0.308,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o4-mini-high","source":"epoch","metric":"epoch_gdpval","value":0.253,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-2.5-pro","source":"epoch","metric":"epoch_gdpval","value":0.233,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4o","source":"epoch","metric":"epoch_gdpval","value":0.099,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_osworld_2","value":0.3143,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://osworld-v2.xlang.ai/"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_osworld_2_partial","value":0.6831,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://osworld-v2.xlang.ai/"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_osworld_2","value":0.27340000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://osworld-v2.xlang.ai/"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_osworld_2_partial","value":0.6272,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://osworld-v2.xlang.ai/"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_osworld_2","value":0.20600000000000002,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://osworld-v2.xlang.ai/"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_osworld_2_partial","value":0.548,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://osworld-v2.xlang.ai/"},{"modelId":"anthropic/claude-opus-4.7","source":"epoch","metric":"epoch_osworld_2","value":0.182,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://osworld-v2.xlang.ai/"},{"modelId":"anthropic/claude-opus-4.7","source":"epoch","metric":"epoch_osworld_2_partial","value":0.4891,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://osworld-v2.xlang.ai/"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_osworld_2","value":0.13,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://osworld-v2.xlang.ai/"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_osworld_2_cost_usd","value":2750,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://osworld-v2.xlang.ai/"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_osworld_2_partial","value":0.495,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://osworld-v2.xlang.ai/"},{"modelId":"anthropic/claude-sonnet-4.6","source":"epoch","metric":"epoch_osworld_2","value":0.09300000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://osworld-v2.xlang.ai/"},{"modelId":"anthropic/claude-sonnet-4.6","source":"epoch","metric":"epoch_osworld_2_cost_usd","value":1550,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://osworld-v2.xlang.ai/"},{"modelId":"anthropic/claude-sonnet-4.6","source":"epoch","metric":"epoch_osworld_2_partial","value":0.339,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://osworld-v2.xlang.ai/"},{"modelId":"minimax/minimax-m3","source":"epoch","metric":"epoch_osworld_2","value":0.046,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://osworld-v2.xlang.ai/"},{"modelId":"minimax/minimax-m3","source":"epoch","metric":"epoch_osworld_2_cost_usd","value":258.78,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://osworld-v2.xlang.ai/"},{"modelId":"minimax/minimax-m3","source":"epoch","metric":"epoch_osworld_2_partial","value":0.223,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://osworld-v2.xlang.ai/"},{"modelId":"moonshotai/kimi-k2.6","source":"epoch","metric":"epoch_osworld_2","value":0.046,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://osworld-v2.xlang.ai/"},{"modelId":"moonshotai/kimi-k2.6","source":"epoch","metric":"epoch_osworld_2_cost_usd","value":708,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://osworld-v2.xlang.ai/"},{"modelId":"moonshotai/kimi-k2.6","source":"epoch","metric":"epoch_osworld_2_partial","value":0.221,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://osworld-v2.xlang.ai/"},{"modelId":"qwen/qwen3.7-plus","source":"epoch","metric":"epoch_osworld_2","value":0.027999999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://osworld-v2.xlang.ai/"},{"modelId":"qwen/qwen3.7-plus","source":"epoch","metric":"epoch_osworld_2_cost_usd","value":411.56,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://osworld-v2.xlang.ai/"},{"modelId":"qwen/qwen3.7-plus","source":"epoch","metric":"epoch_osworld_2_partial","value":0.215,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://osworld-v2.xlang.ai/"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_balrog","value":0.6829999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://balrogai.com/"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_balrog","value":0.634,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://balrogai.com/"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_balrog","value":0.6,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://balrogai.com/"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_balrog","value":0.57,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://balrogai.com/"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_balrog","value":0.532,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://balrogai.com/"},{"modelId":"google/gemini-3-flash-preview","source":"epoch","metric":"epoch_balrog","value":0.48100000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://balrogai.com/"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_balrog","value":0.456,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://balrogai.com/"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_balrog","value":0.435,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://balrogai.com/"},{"modelId":"google/gemini-2.5-flash","source":"epoch","metric":"epoch_balrog","value":0.335,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://balrogai.com/"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_balrog","value":0.32799999999999996,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://balrogai.com/"},{"modelId":"openai/gpt-4o-2024-05-13","source":"epoch","metric":"epoch_balrog","value":0.32299999999999995,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://balrogai.com/"},{"modelId":"anthropic/claude-haiku-4.5","source":"epoch","metric":"epoch_balrog","value":0.312,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://balrogai.com/"},{"modelId":"rekaai/reka-flash-3","source":"epoch","metric":"epoch_balrog","value":0.292,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://balrogai.com/"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"epoch","metric":"epoch_balrog","value":0.27899999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://balrogai.com/"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"epoch","metric":"epoch_balrog","value":0.23,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://balrogai.com/"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"epoch","metric":"epoch_balrog","value":0.174,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://balrogai.com/"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"epoch","metric":"epoch_balrog","value":0.162,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://balrogai.com/"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"epoch","metric":"epoch_balrog","value":0.151,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://balrogai.com/"},{"modelId":"microsoft/phi-4","source":"epoch","metric":"epoch_balrog","value":0.11599999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://balrogai.com/"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"epoch","metric":"epoch_balrog","value":0.10099999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://balrogai.com/"},{"modelId":"qwen/qwen-2.5-7b-instruct","source":"epoch","metric":"epoch_balrog","value":0.078,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://balrogai.com/"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"epoch","metric":"epoch_balrog","value":0.066,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://balrogai.com/"},{"modelId":"anthropic/claude-opus-4.6","source":"epoch","metric":"epoch_deepresearch_bench","value":0.5529999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://evals.futuresearch.ai/#drb"},{"modelId":"anthropic/claude-sonnet-4.6","source":"epoch","metric":"epoch_deepresearch_bench","value":0.549,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://evals.futuresearch.ai/#drb"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_deepresearch_bench","value":0.5479999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://evals.futuresearch.ai/#drb"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_deepresearch_bench","value":0.54,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://evals.futuresearch.ai/#drb"},{"modelId":"anthropic/claude-sonnet-4.5","source":"epoch","metric":"epoch_deepresearch_bench","value":0.526,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://drb.futuresearch.ai"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_deepresearch_bench","value":0.502,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://evals.futuresearch.ai/#drb"},{"modelId":"google/gemini-3-flash-preview","source":"epoch","metric":"epoch_deepresearch_bench","value":0.498,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://evals.futuresearch.ai/#drb"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_deepresearch_bench","value":0.49600000000000005,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://drb.futuresearch.ai"},{"modelId":"anthropic/claude-opus-4.1","source":"epoch","metric":"epoch_deepresearch_bench","value":0.483,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://drb.futuresearch.ai"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_deepresearch_bench","value":0.478,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://evals.futuresearch.ai/#drb"},{"modelId":"anthropic/claude-haiku-4.5","source":"epoch","metric":"epoch_deepresearch_bench","value":0.455,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://evals.futuresearch.ai/#drb"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_deepresearch_bench","value":0.452,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://drb.futuresearch.ai"},{"modelId":"google/gemini-2.5-pro-preview","source":"epoch","metric":"epoch_deepresearch_bench","value":0.428,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://drb.futuresearch.ai"},{"modelId":"openai/gpt-5.1","source":"epoch","metric":"epoch_deepresearch_bench","value":0.428,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://evals.futuresearch.ai/#drb"},{"modelId":"google/gemini-2.5-pro","source":"epoch","metric":"epoch_deepresearch_bench","value":0.41500000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://evals.futuresearch.ai/#drb"},{"modelId":"openai/gpt-5.2","source":"epoch","metric":"epoch_deepresearch_bench","value":0.41100000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://evals.futuresearch.ai/#drb"},{"modelId":"google/gemini-3.1-flash-lite","source":"epoch","metric":"epoch_deepresearch_bench","value":0.373,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://evals.futuresearch.ai/#drb"},{"modelId":"openai/gpt-5.4-mini","source":"epoch","metric":"epoch_deepresearch_bench","value":0.363,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://evals.futuresearch.ai/#drb"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_deepresearch_bench","value":0.35100000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://evals.futuresearch.ai/#drb"},{"modelId":"deepseek/deepseek-r1-0528","source":"epoch","metric":"epoch_deepresearch_bench","value":0.351,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://drb.futuresearch.ai"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_posttrainbench","value":0.4179,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_posttrainbench","value":0.36229999999999996,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_posttrainbench","value":0.3504,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_posttrainbench","value":0.33840000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_posttrainbench","value":0.3196,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_posttrainbench","value":0.317,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.7","source":"epoch","metric":"epoch_posttrainbench","value":0.2856,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_posttrainbench","value":0.2723,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.5","source":"epoch","metric":"epoch_posttrainbench","value":0.2345,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_posttrainbench","value":0.21989999999999998,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_posttrainbench","value":0.19,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-4-argon","source":"epoch","metric":"epoch_gpqa_diamond","value":0.9640151515151515,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"mistralai/mistral-large-4-0","source":"epoch","metric":"epoch_gpqa_diamond","value":0.8806818181818182,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"epoch","metric":"epoch_gpqa_diamond","value":0.8983585858585859,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-haiku-5.5","source":"epoch","metric":"epoch_gpqa_diamond","value":0.8964646464646465,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6.1-sol","source":"epoch","metric":"epoch_gpqa_diamond","value":0.9539141414141414,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-5.5","source":"epoch","metric":"epoch_gpqa_diamond","value":0.9558080808080808,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-luna","source":"epoch","metric":"epoch_gpqa_diamond","value":0.9046717171717171,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.7","source":"epoch","metric":"epoch_gpqa_diamond","value":0.92739898989899,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-sol","source":"epoch","metric":"epoch_gpqa_diamond","value":0.9431818181818182,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-5.5","source":"epoch","metric":"epoch_gpqa_diamond","value":0.9059343434343434,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.8-max-0902","source":"epoch","metric":"epoch_gpqa_diamond","value":0.9267676767676768,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_gpqa_diamond","value":0.9539141414141414,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"ibm-granite/granite-4.0-h-micro","source":"epoch","metric":"epoch_gpqa_diamond","value":0.2828282828282828,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3-32b","source":"epoch","metric":"epoch_gpqa_diamond","value":0.6571969696969697,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"epoch","metric":"epoch_gpqa_diamond","value":0.5561868686868687,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3-30b-a3b","source":"epoch","metric":"epoch_gpqa_diamond","value":0.6167929292929293,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen-2.5-7b-instruct","source":"epoch","metric":"epoch_gpqa_diamond","value":0.3547979797979798,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"epoch","metric":"epoch_gpqa_diamond","value":0.23926767676767677,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-4.7-flash","source":"epoch","metric":"epoch_gpqa_diamond","value":0.6054292929292929,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_gpqa_diamond","value":0.9577020202020202,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"epoch","metric":"epoch_gpqa_diamond","value":0.8345959595959596,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3-14b","source":"epoch","metric":"epoch_gpqa_diamond","value":0.6376262626262627,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemma-3-4b-it","source":"epoch","metric":"epoch_gpqa_diamond","value":0.23232323232323232,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemma-3-12b-it","source":"epoch","metric":"epoch_gpqa_diamond","value":0.39457070707070707,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"epoch","metric":"epoch_gpqa_diamond","value":0.26957070707070707,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.5-9b","source":"epoch","metric":"epoch_gpqa_diamond","value":0.7897727272727273,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemma-3-27b-it","source":"epoch","metric":"epoch_gpqa_diamond","value":0.4772727272727273,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-oss-20b","source":"epoch","metric":"epoch_gpqa_diamond","value":0.6079545454545454,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.3-flash","source":"epoch","metric":"epoch_gpqa_diamond","value":0.9015151515151515,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.3","source":"epoch","metric":"epoch_gpqa_diamond","value":0.9090909090909091,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"epoch","metric":"epoch_gpqa_diamond","value":0.9166666666666666,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.7-flash","source":"epoch","metric":"epoch_gpqa_diamond","value":0.9482323232323232,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"thinkingmachines/inkling-small","source":"epoch","metric":"epoch_gpqa_diamond","value":0.88510101010101,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_gpqa_diamond","value":0.9400252525252525,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"epoch","metric":"epoch_gpqa_diamond","value":0.8535353535353535,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"minimax/minimax-m3","source":"epoch","metric":"epoch_gpqa_diamond","value":0.9090909090909091,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_gpqa_diamond","value":0.9185606060606061,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.1","source":"epoch","metric":"epoch_gpqa_diamond","value":0.898989898989899,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4-mini","source":"epoch","metric":"epoch_gpqa_diamond","value":0.8686868686868687,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_gpqa_diamond","value":0.9349747474747475,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_gpqa_diamond","value":0.9065656565656566,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_gpqa_diamond","value":0.9311868686868687,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_gpqa_diamond","value":0.9330808080808081,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.7-max","source":"epoch","metric":"epoch_gpqa_diamond","value":0.9090909090909091,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_gpqa_diamond","value":0.8181818181818182,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.1","source":"epoch","metric":"epoch_gpqa_diamond","value":0.8762626262626263,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k2.7-code","source":"epoch","metric":"epoch_gpqa_diamond","value":0.8787878787878788,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_gpqa_diamond","value":0.9160353535353535,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.6-plus","source":"epoch","metric":"epoch_gpqa_diamond","value":0.8838383838383839,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_gpqa_diamond","value":0.7960858585858586,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.6-27b","source":"epoch","metric":"epoch_gpqa_diamond","value":0.8585858585858586,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"epoch","metric":"epoch_gpqa_diamond","value":0.8636363636363636,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"epoch","metric":"epoch_gpqa_diamond","value":0.8484848484848485,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.6-flash","source":"epoch","metric":"epoch_gpqa_diamond","value":0.9412878787878788,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.6-35b-a3b","source":"epoch","metric":"epoch_gpqa_diamond","value":0.8484848484848485,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.6-flash","source":"epoch","metric":"epoch_gpqa_diamond","value":0.8333333333333334,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.7-plus","source":"epoch","metric":"epoch_gpqa_diamond","value":0.8787878787878788,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.7-flash","source":"epoch","metric":"epoch_gpqa_diamond","value":0.8232323232323232,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4-nano","source":"epoch","metric":"epoch_gpqa_diamond","value":0.7847,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"epoch","metric":"epoch_gpqa_diamond","value":0.8232323232323232,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_gpqa_diamond","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemma-4-31b-it","source":"epoch","metric":"epoch_gpqa_diamond","value":0.7575757575757576,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemma-4-26b-a4b-it","source":"epoch","metric":"epoch_gpqa_diamond","value":0.7323232323232324,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4-pro","source":"epoch","metric":"epoch_gpqa_diamond","value":0.9090909090909091,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.6","source":"epoch","metric":"epoch_gpqa_diamond","value":0.9053030303030303,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.5-flash-lite","source":"epoch","metric":"epoch_gpqa_diamond","value":0.8333333333333334,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.5-flash","source":"epoch","metric":"epoch_gpqa_diamond","value":0.928030303030303,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_gpqa_diamond","value":0.9444444444444444,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.1-flash-lite","source":"epoch","metric":"epoch_gpqa_diamond","value":0.8181818181818182,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3-flash-preview","source":"epoch","metric":"epoch_gpqa_diamond","value":0.8939393939393939,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-5","source":"epoch","metric":"epoch_gpqa_diamond","value":0.9053030303030303,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-4.6","source":"epoch","metric":"epoch_gpqa_diamond","value":0.8737373737373737,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_gpqa_diamond","value":0.9387626262626263,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_gpqa_diamond","value":0.9103535353535354,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.7","source":"epoch","metric":"epoch_gpqa_diamond","value":0.9015151515151515,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_gpqa_diamond","value":0.8585858585858586,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"thinkingmachines/inkling","source":"epoch","metric":"epoch_gpqa_diamond","value":0.8825757575757576,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"epoch","metric":"epoch_gpqa_diamond","value":0.9103535353535354,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o1","source":"epoch","metric":"epoch_gpqa_diamond","value":0.7676767676767676,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_gpqa_diamond","value":0.8617424242424242,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o3-mini","source":"epoch","metric":"epoch_gpqa_diamond","value":0.7702020202020202,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-chat","source":"epoch","metric":"epoch_gpqa_diamond","value":0.7121212121212122,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_gpqa_diamond","value":0.933,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5-nano","source":"epoch","metric":"epoch_gpqa_diamond","value":0.6944444444444444,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.2","source":"epoch","metric":"epoch_gpqa_diamond","value":0.914,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.5","source":"epoch","metric":"epoch_gpqa_diamond","value":0.9343434343434344,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.3","source":"epoch","metric":"epoch_gpqa_diamond","value":0.8882575757575758,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k2.6","source":"epoch","metric":"epoch_gpqa_diamond","value":0.9078282828282829,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4-pro","source":"epoch","metric":"epoch_gpqa_diamond","value":0.946,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5","source":"epoch","metric":"epoch_gpqa_diamond","value":0.8781725888324873,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-4.7","source":"epoch","metric":"epoch_gpqa_diamond","value":0.8333333333333334,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"epoch","metric":"epoch_gpqa_diamond","value":0.8005050505050505,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-oss-120b","source":"epoch","metric":"epoch_gpqa_diamond","value":0.7575757575757576,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_gpqa_diamond","value":0.860479797979798,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-2.5-pro","source":"epoch","metric":"epoch_gpqa_diamond","value":0.8529040404040404,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-4.5","source":"epoch","metric":"epoch_gpqa_diamond","value":0.8232323232323232,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-haiku-4.5","source":"epoch","metric":"epoch_gpqa_diamond","value":0.7121212121212122,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.1","source":"epoch","metric":"epoch_gpqa_diamond","value":0.7727272727272727,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-2.5-pro-preview","source":"epoch","metric":"epoch_gpqa_diamond","value":0.8484848484848485,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-r1-0528","source":"epoch","metric":"epoch_gpqa_diamond","value":0.7632575757575758,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4.1-mini","source":"epoch","metric":"epoch_gpqa_diamond","value":0.6584595959595959,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4.1-nano","source":"epoch","metric":"epoch_gpqa_diamond","value":0.48926767676767674,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4.1","source":"epoch","metric":"epoch_gpqa_diamond","value":0.6691919191919192,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta-llama/llama-4-scout","source":"epoch","metric":"epoch_gpqa_diamond","value":0.5183080808080808,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen-plus","source":"epoch","metric":"epoch_gpqa_diamond","value":0.4810606060606061,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"epoch","metric":"epoch_gpqa_diamond","value":0.6761363636363636,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4o-2024-11-20","source":"epoch","metric":"epoch_gpqa_diamond","value":0.4788510101010101,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"microsoft/phi-4","source":"epoch","metric":"epoch_gpqa_diamond","value":0.5606060606060606,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4o-2024-08-06","source":"epoch","metric":"epoch_gpqa_diamond","value":0.49210858585858586,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemma-2-27b-it","source":"epoch","metric":"epoch_gpqa_diamond","value":0.3648989898989899,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4o-2024-05-13","source":"epoch","metric":"epoch_gpqa_diamond","value":0.4889520202020202,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"epoch","metric":"epoch_gpqa_diamond","value":0.37720959595959597,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"epoch","metric":"epoch_gpqa_diamond","value":0.44191919191919193,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"epoch","metric":"epoch_gpqa_diamond","value":0.4914772727272727,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"mistralai/mistral-large-2407","source":"epoch","metric":"epoch_gpqa_diamond","value":0.49021464646464646,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"epoch","metric":"epoch_gpqa_diamond","value":0.4744318181818182,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_arc_agi","value":0.985,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_arc_agi","value":0.985,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"anthropic/claude-opus-5.5","source":"epoch","metric":"epoch_arc_agi","value":0.985,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/gpt-6.1-sol","source":"epoch","metric":"epoch_arc_agi","value":0.985,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_arc_agi","value":0.985,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"google/gemini-4-argon","source":"epoch","metric":"epoch_arc_agi","value":0.985,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_arc_agi","value":0.98,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.5223,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_arc_agi","value":0.975,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.4,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_arc_agi","value":0.975,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"anthropic/claude-fable-5.1","source":"epoch","metric":"epoch_arc_agi","value":0.975,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/gpt-5.5-pro","source":"epoch","metric":"epoch_arc_agi","value":0.965,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/gpt-5.5-pro","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":4.53,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_arc_agi","value":0.965,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.55,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"google/gemini-3.7-flash","source":"epoch","metric":"epoch_arc_agi","value":0.9550000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/gpt-6-sol","source":"epoch","metric":"epoch_arc_agi","value":0.9550000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_arc_agi","value":0.9500000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.73,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/gpt-5.4-pro","source":"epoch","metric":"epoch_arc_agi","value":0.9450000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4-pro","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":7.21,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_arc_agi","value":0.9450000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.770482,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"epoch","metric":"epoch_arc_agi","value":0.9450000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"anthropic/claude-opus-4.6","source":"epoch","metric":"epoch_arc_agi","value":0.9400000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_arc_agi","value":0.9367000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.62,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.7","source":"epoch","metric":"epoch_arc_agi","value":0.935,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.7","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":1.41,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.5-flash","source":"epoch","metric":"epoch_arc_agi","value":0.925,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"google/gemini-3.5-flash","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.4278,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_arc_agi","value":0.925,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":2.332,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"google/gemini-3.6-flash","source":"epoch","metric":"epoch_arc_agi","value":0.9116666666666666,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"z-ai/glm-5.3-flash","source":"epoch","metric":"epoch_arc_agi","value":0.91,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/gpt-5.2-pro","source":"epoch","metric":"epoch_arc_agi","value":0.905,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.2-pro","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":11.6542,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"epoch","metric":"epoch_arc_agi","value":0.905,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"x-ai/grok-4.7","source":"epoch","metric":"epoch_arc_agi","value":0.9016666666666666,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"x-ai/grok-4.20","source":"epoch","metric":"epoch_arc_agi","value":0.895,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"x-ai/grok-4.20","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.35,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"epoch","metric":"epoch_arc_agi","value":0.89,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"anthropic/claude-haiku-5.5","source":"epoch","metric":"epoch_arc_agi","value":0.89,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_arc_agi","value":0.88,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.32,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_arc_agi","value":0.875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"qwen/qwen3.8-27b","source":"epoch","metric":"epoch_arc_agi","value":0.875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"x-ai/grok-4.5","source":"epoch","metric":"epoch_arc_agi","value":0.8717,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"x-ai/grok-4.5","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.31,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/gpt-6-luna","source":"epoch","metric":"epoch_arc_agi","value":0.8666666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.6","source":"epoch","metric":"epoch_arc_agi","value":0.865,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-4.6","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":1.1908,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.2","source":"epoch","metric":"epoch_arc_agi","value":0.862,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/gpt-5.2","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.96,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"google/gemini-3-flash-preview","source":"epoch","metric":"epoch_arc_agi","value":0.8467,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"google/gemini-3-flash-preview","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.1743,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"thinkingmachines/inkling-small","source":"epoch","metric":"epoch_arc_agi","value":0.84,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_arc_agi","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":1.47,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"thinkingmachines/inkling","source":"epoch","metric":"epoch_arc_agi","value":0.795,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"thinkingmachines/inkling","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.300474,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_arc_agi","value":0.77,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.1916,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/gpt-5.1","source":"epoch","metric":"epoch_arc_agi","value":0.7283,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/gpt-5-pro","source":"epoch","metric":"epoch_arc_agi","value":0.702,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_arc_agi","value":0.6567000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.5087,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"moonshotai/kimi-k2.5","source":"epoch","metric":"epoch_arc_agi","value":0.6533,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k2.5","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.15,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-4.5","source":"epoch","metric":"epoch_arc_agi","value":0.6367,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-4.5","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.5193,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"minimax/minimax-m2.5","source":"epoch","metric":"epoch_arc_agi","value":0.6367,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"minimax/minimax-m2.5","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.07,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4-mini","source":"epoch","metric":"epoch_arc_agi","value":0.6367,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/gpt-5.4-mini","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.51,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_arc_agi","value":0.6083,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.5002,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/o3-pro","source":"epoch","metric":"epoch_arc_agi","value":0.5933,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/o3-pro","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":4.16,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_arc_agi","value":0.5867,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.4058,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"deepseek/deepseek-v3.2","source":"epoch","metric":"epoch_arc_agi","value":0.57,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v3.2","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.08,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_arc_agi","value":0.5433,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.116,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.5-flash-lite","source":"epoch","metric":"epoch_arc_agi","value":0.535,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/gpt-5.4-nano","source":"epoch","metric":"epoch_arc_agi","value":0.515,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/gpt-5.4-nano","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.13,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"anthropic/claude-haiku-4.5","source":"epoch","metric":"epoch_arc_agi","value":0.4767,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-haiku-4.5","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.2558,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5","source":"epoch","metric":"epoch_arc_agi","value":0.44670000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.17,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-2.5-pro","source":"epoch","metric":"epoch_arc_agi","value":0.41000000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-2.5-pro","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.4839,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o3-mini","source":"epoch","metric":"epoch_arc_agi","value":0.345,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/o3-mini","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.3989,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"google/gemini-2.5-flash","source":"epoch","metric":"epoch_arc_agi","value":0.3333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"google/gemini-2.5-flash","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.2134,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/o1","source":"epoch","metric":"epoch_arc_agi","value":0.307,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/o1-pro","source":"epoch","metric":"epoch_arc_agi","value":0.233,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"deepseek/deepseek-r1-0528","source":"epoch","metric":"epoch_arc_agi","value":0.2121,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"deepseek/deepseek-r1-0528","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.0464,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/gpt-5-nano","source":"epoch","metric":"epoch_arc_agi","value":0.2071,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5-nano","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.0124,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"epoch","metric":"epoch_arc_agi","value":0.11,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.0025,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4.1","source":"epoch","metric":"epoch_arc_agi","value":0.055,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/gpt-4.1","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.039,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/gpt-4o","source":"epoch","metric":"epoch_arc_agi","value":0.045,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/gpt-4o","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.05,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"meta-llama/llama-4-maverick","source":"epoch","metric":"epoch_arc_agi","value":0.0438,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"meta-llama/llama-4-maverick","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.0078,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/gpt-4.1-mini","source":"epoch","metric":"epoch_arc_agi","value":0.035,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/gpt-4.1-mini","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.0078,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"meta-llama/llama-4-scout","source":"epoch","metric":"epoch_arc_agi","value":0.005,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"meta-llama/llama-4-scout","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.0041,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/gpt-4.1-nano","source":"epoch","metric":"epoch_arc_agi","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/gpt-4.1-nano","source":"epoch","metric":"epoch_arc_agi_cost_usd","value":0.0021,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://arcprize.org/leaderboard"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_arc_agi_2","value":0.9500000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6.1-sol","source":"epoch","metric":"epoch_arc_agi_2","value":0.9416666666666668,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-5.5","source":"epoch","metric":"epoch_arc_agi_2","value":0.9333333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_arc_agi_2","value":0.925,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":1.44,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-4-argon","source":"epoch","metric":"epoch_arc_agi_2","value":0.9125,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_arc_agi_2","value":0.9042,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-fable-5.1","source":"epoch","metric":"epoch_arc_agi_2","value":0.9,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-sol","source":"epoch","metric":"epoch_arc_agi_2","value":0.8958333333333335,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_arc_agi_2","value":0.8916666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_arc_agi_2","value":0.8916666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_arc_agi_2","value":0.85,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":1.87,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.7-flash","source":"epoch","metric":"epoch_arc_agi_2","value":0.8458333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.5-pro","source":"epoch","metric":"epoch_arc_agi_2","value":0.8458,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.5-pro","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":10.51,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_arc_agi_2","value":0.839,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":1.09,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4-pro","source":"epoch","metric":"epoch_arc_agi_2","value":0.8333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4-pro","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":16.41,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_arc_agi_2","value":0.771,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":0.9622,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.7","source":"epoch","metric":"epoch_arc_agi_2","value":0.7583,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_arc_agi_2","value":0.7395,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":1.52,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"epoch","metric":"epoch_arc_agi_2","value":0.7291666666666666,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.5-flash","source":"epoch","metric":"epoch_arc_agi_2","value":0.7208,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.5-flash","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":0.8503,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_arc_agi_2","value":0.7208,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":2.7425,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.6","source":"epoch","metric":"epoch_arc_agi_2","value":0.6917,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_arc_agi_2","value":0.6708333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.3-flash","source":"epoch","metric":"epoch_arc_agi_2","value":0.6583333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.20","source":"epoch","metric":"epoch_arc_agi_2","value":0.6514,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.20","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":0.92,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"epoch","metric":"epoch_arc_agi_2","value":0.6138888888888888,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.7","source":"epoch","metric":"epoch_arc_agi_2","value":0.6138888888888888,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"epoch","metric":"epoch_arc_agi_2","value":0.6125,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-haiku-5.5","source":"epoch","metric":"epoch_arc_agi_2","value":0.6125,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-4.6","source":"epoch","metric":"epoch_arc_agi_2","value":0.6042,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-4.6","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":2.6966,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_arc_agi_2","value":0.6041666666666666,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":1.592694,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.6-flash","source":"epoch","metric":"epoch_arc_agi_2","value":0.6041666666666666,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_arc_agi_2","value":0.5954,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":0.67,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-luna","source":"epoch","metric":"epoch_arc_agi_2","value":0.5930555555555556,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.2-pro","source":"epoch","metric":"epoch_arc_agi_2","value":0.5416,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.2-pro","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":15.721,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.2","source":"epoch","metric":"epoch_arc_agi_2","value":0.5291,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.2","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":1.8982,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.5","source":"epoch","metric":"epoch_arc_agi_2","value":0.5264,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.5","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":0.78,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.8-27b","source":"epoch","metric":"epoch_arc_agi_2","value":0.4236111111111111,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"thinkingmachines/inkling-small","source":"epoch","metric":"epoch_arc_agi_2","value":0.40138888888888885,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_arc_agi_2","value":0.3764,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":2.4,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"thinkingmachines/inkling","source":"epoch","metric":"epoch_arc_agi_2","value":0.3652777777777778,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"thinkingmachines/inkling","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":0.642077,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3-flash-preview","source":"epoch","metric":"epoch_arc_agi_2","value":0.3361,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_arc_agi_2","value":0.22775000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":0.2501,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4-mini","source":"epoch","metric":"epoch_arc_agi_2","value":0.189,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4-mini","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":0.75,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5-pro","source":"epoch","metric":"epoch_arc_agi_2","value":0.1833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5-pro","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":7.1432,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.1","source":"epoch","metric":"epoch_arc_agi_2","value":0.1764,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.1","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":1.1704,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-4.5","source":"epoch","metric":"epoch_arc_agi_2","value":0.1361,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-4.5","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":0.7589,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k2.5","source":"epoch","metric":"epoch_arc_agi_2","value":0.11810000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k2.5","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":0.28,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.5-flash-lite","source":"epoch","metric":"epoch_arc_agi_2","value":0.10277777777777779,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_arc_agi_2","value":0.0986,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":0.7302,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_arc_agi_2","value":0.0653,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":0.8339,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_arc_agi_2","value":0.0611,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":0.856,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4-nano","source":"epoch","metric":"epoch_arc_agi_2","value":0.0569,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4-nano","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":0.16,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o3-pro","source":"epoch","metric":"epoch_arc_agi_2","value":0.0486,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o3-pro","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":7.5516,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-2.5-pro","source":"epoch","metric":"epoch_arc_agi_2","value":0.0486,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-2.5-pro","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":0.757,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"minimax/minimax-m2.5","source":"epoch","metric":"epoch_arc_agi_2","value":0.0486,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"minimax/minimax-m2.5","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":0.17,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5","source":"epoch","metric":"epoch_arc_agi_2","value":0.0486,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":0.27,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_arc_agi_2","value":0.0444,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":0.1977,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-haiku-4.5","source":"epoch","metric":"epoch_arc_agi_2","value":0.0403,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-haiku-4.5","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":0.3766,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v3.2","source":"epoch","metric":"epoch_arc_agi_2","value":0.0403,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v3.2","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":0.12,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o3-mini","source":"epoch","metric":"epoch_arc_agi_2","value":0.0299,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o3-mini","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":0.5472,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5-nano","source":"epoch","metric":"epoch_arc_agi_2","value":0.026100000000000005,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5-nano","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":0.0295,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-2.5-flash","source":"epoch","metric":"epoch_arc_agi_2","value":0.025400000000000002,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-2.5-flash","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":0.3191,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"epoch","metric":"epoch_arc_agi_2","value":0.0125,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":0.0044,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-r1-0528","source":"epoch","metric":"epoch_arc_agi_2","value":0.0112,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-r1-0528","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":0.0527,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4.1","source":"epoch","metric":"epoch_arc_agi_2","value":0.0042,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4.1","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":0.0691,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4o-mini","source":"epoch","metric":"epoch_arc_agi_2","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4o-mini","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":0.01,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4.1-nano","source":"epoch","metric":"epoch_arc_agi_2","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4.1-nano","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":0.0036,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta-llama/llama-4-scout","source":"epoch","metric":"epoch_arc_agi_2","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta-llama/llama-4-scout","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":0.0062,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta-llama/llama-4-maverick","source":"epoch","metric":"epoch_arc_agi_2","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta-llama/llama-4-maverick","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":0.0121,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4.1-mini","source":"epoch","metric":"epoch_arc_agi_2","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4.1-mini","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":0.0139,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4o","source":"epoch","metric":"epoch_arc_agi_2","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4o","source":"epoch","metric":"epoch_arc_agi_2_cost_usd","value":0.08,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_hle","value":0.5479999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-fable-5.1","source":"epoch","metric":"epoch_hle","value":0.465,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_hle","value":0.4644,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-5.5","source":"epoch","metric":"epoch_hle","value":0.4612,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_hle","value":0.44520000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4-pro","source":"epoch","metric":"epoch_hle","value":0.4432,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_hle","value":0.3624,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.7","source":"epoch","metric":"epoch_hle","value":0.362,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.6","source":"epoch","metric":"epoch_hle","value":0.3444,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5-pro","source":"epoch","metric":"epoch_hle","value":0.3164,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-haiku-5.5","source":"epoch","metric":"epoch_hle","value":0.3012,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.2","source":"epoch","metric":"epoch_hle","value":0.278,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_hle","value":0.2532,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_hle","value":0.252,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k2.5","source":"epoch","metric":"epoch_hle","value":0.24370000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.1","source":"epoch","metric":"epoch_hle","value":0.2368,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-2.5-pro-preview","source":"epoch","metric":"epoch_hle","value":0.2164,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_hle","value":0.20320000000000002,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_hle","value":0.19440000000000002,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_hle","value":0.1808,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-4.5","source":"epoch","metric":"epoch_hle","value":0.13720000000000002,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-2.5-flash","source":"epoch","metric":"epoch_hle","value":0.1208,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.1","source":"epoch","metric":"epoch_hle","value":0.1152,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"epoch","metric":"epoch_hle","value":0.0864,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-4.5","source":"epoch","metric":"epoch_hle","value":0.08320000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-4.5-air","source":"epoch","metric":"epoch_hle","value":0.0812,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o1-pro","source":"epoch","metric":"epoch_hle","value":0.0812,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o1","source":"epoch","metric":"epoch_hle","value":0.0796,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta-llama/llama-4-maverick","source":"epoch","metric":"epoch_hle","value":0.056799999999999996,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4.1","source":"epoch","metric":"epoch_hle","value":0.054000000000000006,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"mistralai/mistral-medium-3","source":"epoch","metric":"epoch_hle","value":0.0452,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"amazon/nova-pro-v1","source":"epoch","metric":"epoch_hle","value":0.044000000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"amazon/nova-lite-v1","source":"epoch","metric":"epoch_hle","value":0.0364,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4o-2024-11-20","source":"epoch","metric":"epoch_hle","value":0.027200000000000002,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_simplebench","value":0.8190000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_simplebench","value":0.8059999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://lmcouncil.ai/benchmarks"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_simplebench","value":0.7959999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://simple-bench.com/"},{"modelId":"openai/gpt-5.5-pro","source":"epoch","metric":"epoch_simplebench","value":0.7690000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://lmcouncil.ai/benchmarks"},{"modelId":"google/gemini-3.5-flash","source":"epoch","metric":"epoch_simplebench","value":0.767,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_simplebench","value":0.7590000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://lmcouncil.ai/benchmarks"},{"modelId":"meta/muse-spark-1.2","source":"epoch","metric":"epoch_simplebench","value":0.745,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://lmcouncil.ai/benchmarks"},{"modelId":"openai/gpt-5.4-pro","source":"epoch","metric":"epoch_simplebench","value":0.741,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://simple-bench.com/"},{"modelId":"openai/gpt-5.6-sol-pro","source":"epoch","metric":"epoch_simplebench","value":0.7170000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://lmcouncil.ai/benchmarks"},{"modelId":"qwen/qwen3.7-max","source":"epoch","metric":"epoch_simplebench","value":0.7040000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.5","source":"epoch","metric":"epoch_simplebench","value":0.7000000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://lmcouncil.ai/benchmarks"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_simplebench","value":0.6900000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://lmcouncil.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.6","source":"epoch","metric":"epoch_simplebench","value":0.6759999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://simple-bench.com/"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_simplebench","value":0.648,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://lmcouncil.ai/benchmarks"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_simplebench","value":0.648,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-2.5-pro-preview","source":"epoch","metric":"epoch_simplebench","value":0.624,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://simple-bench.com/"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_simplebench","value":0.62,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://simple-bench.com/"},{"modelId":"anthropic/claude-opus-4.7","source":"epoch","metric":"epoch_simplebench","value":0.617,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://lmcouncil.ai/benchmarks"},{"modelId":"openai/gpt-5-pro","source":"epoch","metric":"epoch_simplebench","value":0.616,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://simple-bench.com/"},{"modelId":"google/gemini-3-flash-preview","source":"epoch","metric":"epoch_simplebench","value":0.611,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://simple-bench.com/"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"epoch","metric":"epoch_simplebench","value":0.611,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://lmcouncil.ai/benchmarks"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_simplebench","value":0.6070000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://lmcouncil.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-5","source":"epoch","metric":"epoch_simplebench","value":0.606,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.1","source":"epoch","metric":"epoch_simplebench","value":0.6,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://simple-bench.com/"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_simplebench","value":0.588,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://lmcouncil.ai/benchmarks"},{"modelId":"moonshotai/kimi-k2.7-code","source":"epoch","metric":"epoch_simplebench","value":0.579,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://lmcouncil.ai/benchmarks"},{"modelId":"openai/gpt-5.2-pro","source":"epoch","metric":"epoch_simplebench","value":0.574,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://simple-bench.com/"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_simplebench","value":0.5670000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://simple-bench.com/"},{"modelId":"z-ai/glm-5.1","source":"epoch","metric":"epoch_simplebench","value":0.551,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-4.5","source":"epoch","metric":"epoch_simplebench","value":0.543,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://simple-bench.com/"},{"modelId":"openai/gpt-5.1","source":"epoch","metric":"epoch_simplebench","value":0.532,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://simple-bench.com/"},{"modelId":"z-ai/glm-5","source":"epoch","metric":"epoch_simplebench","value":0.532,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_simplebench","value":0.531,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://simple-bench.com/"},{"modelId":"thinkingmachines/inkling","source":"epoch","metric":"epoch_simplebench","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://lmcouncil.ai/benchmarks"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_simplebench","value":0.489,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-4.7","source":"epoch","metric":"epoch_simplebench","value":0.47700000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_simplebench","value":0.468,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k2.5","source":"epoch","metric":"epoch_simplebench","value":0.46799999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4-flash","source":"epoch","metric":"epoch_simplebench","value":0.46299999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://lmcouncil.ai/benchmarks"},{"modelId":"openai/gpt-5.2","source":"epoch","metric":"epoch_simplebench","value":0.458,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://simple-bench.com/"},{"modelId":"minimax/minimax-m3","source":"epoch","metric":"epoch_simplebench","value":0.45799999999999996,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://lmcouncil.ai/benchmarks"},{"modelId":"google/gemini-2.5-flash","source":"epoch","metric":"epoch_simplebench","value":0.412,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://simple-bench.com/"},{"modelId":"deepseek/deepseek-r1-0528","source":"epoch","metric":"epoch_simplebench","value":0.408,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://simple-bench.com/"},{"modelId":"openai/o1","source":"epoch","metric":"epoch_simplebench","value":0.401,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://simple-bench.com/"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_simplebench","value":0.387,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://simple-bench.com/"},{"modelId":"qwen/qwen3.6-flash","source":"epoch","metric":"epoch_simplebench","value":0.352,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta-llama/llama-4-maverick","source":"epoch","metric":"epoch_simplebench","value":0.277,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://simple-bench.com/"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"epoch","metric":"epoch_simplebench","value":0.272,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://simple-bench.com/"},{"modelId":"openai/gpt-4.1","source":"epoch","metric":"epoch_simplebench","value":0.27,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://simple-bench.com/"},{"modelId":"moonshotai/kimi-k2","source":"epoch","metric":"epoch_simplebench","value":0.263,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://simple-bench.com/"},{"modelId":"openai/o3-mini","source":"epoch","metric":"epoch_simplebench","value":0.228,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://simple-bench.com/"},{"modelId":"mistralai/mistral-large-2407","source":"epoch","metric":"epoch_simplebench","value":0.225,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://simple-bench.com/"},{"modelId":"openai/gpt-oss-120b","source":"epoch","metric":"epoch_simplebench","value":0.221,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://simple-bench.com/"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"epoch","metric":"epoch_simplebench","value":0.199,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://simple-bench.com/"},{"modelId":"openai/gpt-4o-2024-08-06","source":"epoch","metric":"epoch_simplebench","value":0.178,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://simple-bench.com/"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"epoch","metric":"epoch_simplebench","value":0.107,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://simple-bench.com/"},{"modelId":"mistralai/mistral-large-4-0","source":"epoch","metric":"epoch_chess_puzzles","value":0.33,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-astra-pro","source":"epoch","metric":"epoch_chess_puzzles","value":0.76,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4-nano","source":"epoch","metric":"epoch_chess_puzzles","value":0.45,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.2","source":"epoch","metric":"epoch_chess_puzzles","value":0.48,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5-pro","source":"epoch","metric":"epoch_chess_puzzles","value":0.48,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.2-pro","source":"epoch","metric":"epoch_chess_puzzles","value":0.6,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4-pro","source":"epoch","metric":"epoch_chess_puzzles","value":0.59,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.5-pro","source":"epoch","metric":"epoch_chess_puzzles","value":0.62,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-sol-pro","source":"epoch","metric":"epoch_chess_puzzles","value":0.68,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-4.7","source":"epoch","metric":"epoch_chess_puzzles","value":0.21,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.1","source":"epoch","metric":"epoch_chess_puzzles","value":0.2,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_chess_puzzles","value":0.22,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.3","source":"epoch","metric":"epoch_chess_puzzles","value":0.37,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k2.6","source":"epoch","metric":"epoch_chess_puzzles","value":0.2,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-4-argon","source":"epoch","metric":"epoch_chess_puzzles","value":0.59,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k2.7-code","source":"epoch","metric":"epoch_chess_puzzles","value":0.14,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_chess_puzzles","value":0.37,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.3-flash","source":"epoch","metric":"epoch_chess_puzzles","value":0.21,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"epoch","metric":"epoch_chess_puzzles","value":0.03,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o1","source":"epoch","metric":"epoch_chess_puzzles","value":0.1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4.1","source":"epoch","metric":"epoch_chess_puzzles","value":0.03,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4o-2024-08-06","source":"epoch","metric":"epoch_chess_puzzles","value":0.06,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o3-mini","source":"epoch","metric":"epoch_chess_puzzles","value":0.15,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4.1-nano","source":"epoch","metric":"epoch_chess_puzzles","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_chess_puzzles","value":0.22,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4.1-mini","source":"epoch","metric":"epoch_chess_puzzles","value":0.01,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_chess_puzzles","value":0.24,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_chess_puzzles","value":0.37,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5-nano","source":"epoch","metric":"epoch_chess_puzzles","value":0.22,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_chess_puzzles","value":0.36,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.1","source":"epoch","metric":"epoch_chess_puzzles","value":0.42,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_chess_puzzles","value":0.48,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4-mini","source":"epoch","metric":"epoch_chess_puzzles","value":0.23,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_chess_puzzles","value":0.63,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_chess_puzzles","value":0.43,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_chess_puzzles","value":0.47,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_chess_puzzles","value":0.59,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-4.5","source":"epoch","metric":"epoch_chess_puzzles","value":0.1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"minimax/minimax-m3","source":"epoch","metric":"epoch_chess_puzzles","value":0.13,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-4.6","source":"epoch","metric":"epoch_chess_puzzles","value":0.23,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-haiku-4.5","source":"epoch","metric":"epoch_chess_puzzles","value":0.08,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.6","source":"epoch","metric":"epoch_chess_puzzles","value":0.21,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_chess_puzzles","value":0.14,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_chess_puzzles","value":0.74,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3-flash-preview","source":"epoch","metric":"epoch_chess_puzzles","value":0.39,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-sol","source":"epoch","metric":"epoch_chess_puzzles","value":0.56,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"epoch","metric":"epoch_chess_puzzles","value":0.08,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"epoch","metric":"epoch_chess_puzzles","value":0.14,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.6-plus","source":"epoch","metric":"epoch_chess_puzzles","value":0.14,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4-pro","source":"epoch","metric":"epoch_chess_puzzles","value":0.19,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-luna","source":"epoch","metric":"epoch_chess_puzzles","value":0.36,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.7","source":"epoch","metric":"epoch_chess_puzzles","value":0.41,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_chess_puzzles","value":0.52,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_chess_puzzles","value":0.47,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.3","source":"epoch","metric":"epoch_chess_puzzles","value":0.18,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_chess_puzzles","value":0.51,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.5-flash","source":"epoch","metric":"epoch_chess_puzzles","value":0.45,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.6-flash","source":"epoch","metric":"epoch_chess_puzzles","value":0.12,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.7-max","source":"epoch","metric":"epoch_chess_puzzles","value":0.26,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"epoch","metric":"epoch_chess_puzzles","value":0.32,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.5-flash-lite","source":"epoch","metric":"epoch_chess_puzzles","value":0.21,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-5","source":"epoch","metric":"epoch_chess_puzzles","value":0.45,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_chess_puzzles","value":0.43,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.6-flash","source":"epoch","metric":"epoch_chess_puzzles","value":0.42,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.5","source":"epoch","metric":"epoch_chess_puzzles","value":0.35,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_chess_puzzles","value":0.33,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.8-max-0902","source":"epoch","metric":"epoch_chess_puzzles","value":0.46,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"epoch","metric":"epoch_chess_puzzles","value":0.46,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta/muse-spark-1.1","source":"epoch","metric":"epoch_chess_puzzles","value":0.34,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-fable-5.1","source":"epoch","metric":"epoch_chess_puzzles","value":0.48,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta/muse-spark-1.2","source":"epoch","metric":"epoch_chess_puzzles","value":0.27,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-5.5","source":"epoch","metric":"epoch_chess_puzzles","value":0.67,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-5.5","source":"epoch","metric":"epoch_chess_puzzles","value":0.59,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta/muse-spark-1.3","source":"epoch","metric":"epoch_chess_puzzles","value":0.37,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.7-flash","source":"epoch","metric":"epoch_chess_puzzles","value":0.66,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"thinkingmachines/inkling","source":"epoch","metric":"epoch_chess_puzzles","value":0.21,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6.1-sol","source":"epoch","metric":"epoch_chess_puzzles","value":0.68,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-haiku-5.5","source":"epoch","metric":"epoch_chess_puzzles","value":0.55,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"epoch","metric":"epoch_chess_puzzles","value":0.48,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.7","source":"epoch","metric":"epoch_chess_puzzles","value":0.41,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_chess_puzzles","value":0.58,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"mistralai/mistral-large-4-0","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.17,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-4-argon","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.64,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.43,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-haiku-5.5","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.3,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6.1-sol","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-5.5","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.71,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-5.5","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.65,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-luna","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.07,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.7","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.29,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-sol","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.56,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta/muse-spark-1.3","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.25,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.47,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-fable-5.1","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.58,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.3","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.33,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.37,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.21,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.84,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.26,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k2.6","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.18,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.3-flash","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.08,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.7-flash","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.15,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.35,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.2","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.23,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.56,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.7-plus","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.17,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.29,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.05,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.6-flash","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.18,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.58,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"minimax/minimax-m3","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.08,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.7-max","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.32,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o3-mini","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.07,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.1","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.19,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.23,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4-nano","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.09,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.6-27b","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.07,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.18,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.19,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.17,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4-mini","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.11,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.2,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.6-plus","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.12,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.17,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.6-35b-a3b","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.22,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5-nano","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.09,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-oss-120b","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.02,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4-pro","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.17,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.2,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4.1-mini","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.07,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.09,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.12,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.43,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"thinkingmachines/inkling-small","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.06,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.7-flash","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.37,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.34,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-4.6","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.16,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.59,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.7","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.28,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.6","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.25,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.34,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-5","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.35,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.5-flash","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.32,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.6-flash","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.3,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3-flash-preview","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.26,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.5-flash-lite","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.19,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.34,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.8-max-0902","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.38,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.52,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.36,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-4.5","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.17,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.1","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.21,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_mystery_game_puzzles","value":0.22,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-4-argon","source":"epoch","metric":"epoch_ebr_bench","value":0.6476190476190476,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-haiku-5.5","source":"epoch","metric":"epoch_ebr_bench","value":0.43809523809523804,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6.1-sol","source":"epoch","metric":"epoch_ebr_bench","value":0.5428571428571429,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-5.5","source":"epoch","metric":"epoch_ebr_bench","value":0.7142857142857142,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-sol","source":"epoch","metric":"epoch_ebr_bench","value":0.5333333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-fable-5.1","source":"epoch","metric":"epoch_ebr_bench","value":0.5714285714285714,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_ebr_bench","value":0.45714285714285713,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_ebr_bench","value":0.4476190476190475,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_ebr_bench","value":0.7619047619047619,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_ebr_bench","value":0.30476190476190473,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_ebr_bench","value":0.2857142857142857,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_ebr_bench","value":0.3428571428571428,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_ebr_bench","value":0.395238,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.7","source":"epoch","metric":"epoch_ebr_bench","value":0.19047619047619047,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.6","source":"epoch","metric":"epoch_ebr_bench","value":0.126984,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_ebr_bench","value":0.126984,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_ebr_bench","value":0.09523809523809523,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.2","source":"epoch","metric":"epoch_ebr_bench","value":0.230159,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.7-max","source":"epoch","metric":"epoch_ebr_bench","value":0.09523809523809523,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_ebr_bench","value":0.253968,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.5-flash","source":"epoch","metric":"epoch_ebr_bench","value":0.047619047619047616,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_ebr_bench","value":0.14285714285714285,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k2.6","source":"epoch","metric":"epoch_ebr_bench","value":0.023809523809523808,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-4.5","source":"epoch","metric":"epoch_ebr_bench","value":0.023809523809523808,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.1","source":"epoch","metric":"epoch_ebr_bench","value":0.079365,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_ebr_bench","value":0.14285714285714285,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-4-argon","source":"epoch","metric":"epoch_otis_mock_aime","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"mistralai/mistral-large-4-0","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9833333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9833333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-haiku-5.5","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9888888888888889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6.1-sol","source":"epoch","metric":"epoch_otis_mock_aime","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-5.5","source":"epoch","metric":"epoch_otis_mock_aime","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-luna","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9888888888888889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.7","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9805555555555555,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-sol","source":"epoch","metric":"epoch_otis_mock_aime","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-5.5","source":"epoch","metric":"epoch_otis_mock_aime","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta/muse-spark-1.3","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9916666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.8-max-0902","source":"epoch","metric":"epoch_otis_mock_aime","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9888888888888889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-fable-5.1","source":"epoch","metric":"epoch_otis_mock_aime","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"ibm-granite/granite-4.0-h-micro","source":"epoch","metric":"epoch_otis_mock_aime","value":0.027777777777777776,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"epoch","metric":"epoch_otis_mock_aime","value":0.7,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3-32b","source":"epoch","metric":"epoch_otis_mock_aime","value":0.6694444444444444,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"epoch","metric":"epoch_otis_mock_aime","value":0.6222222222222222,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3-30b-a3b","source":"epoch","metric":"epoch_otis_mock_aime","value":0.6277777777777778,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3-14b","source":"epoch","metric":"epoch_otis_mock_aime","value":0.6638888888888889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen-2.5-7b-instruct","source":"epoch","metric":"epoch_otis_mock_aime","value":0.025,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"epoch","metric":"epoch_otis_mock_aime","value":0.005555555555555556,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-4.7-flash","source":"epoch","metric":"epoch_otis_mock_aime","value":0.5833333333333334,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_otis_mock_aime","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemma-4-26b-a4b-it","source":"epoch","metric":"epoch_otis_mock_aime","value":0.8222222222222222,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemma-3-4b-it","source":"epoch","metric":"epoch_otis_mock_aime","value":0.075,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemma-3-12b-it","source":"epoch","metric":"epoch_otis_mock_aime","value":0.16666666666666666,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"epoch","metric":"epoch_otis_mock_aime","value":0.016666666666666666,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.5-9b","source":"epoch","metric":"epoch_otis_mock_aime","value":0.6166666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemma-3-27b-it","source":"epoch","metric":"epoch_otis_mock_aime","value":0.225,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-oss-20b","source":"epoch","metric":"epoch_otis_mock_aime","value":0.6527777777777778,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.3-flash","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9388888888888889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.3","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9111111111111111,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9861111111111112,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.7-flash","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9722222222222222,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"thinkingmachines/inkling-small","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9916666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"epoch","metric":"epoch_otis_mock_aime","value":0.8666666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"minimax/minimax-m3","source":"epoch","metric":"epoch_otis_mock_aime","value":0.7111111111111111,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_otis_mock_aime","value":0.8638888888888889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.1","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9333333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4-mini","source":"epoch","metric":"epoch_otis_mock_aime","value":0.8888888888888888,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_otis_mock_aime","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_otis_mock_aime","value":0.8444444444444444,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9722222222222222,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9972222222222222,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.7-max","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9555555555555556,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_otis_mock_aime","value":0.8444444444444444,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.1","source":"epoch","metric":"epoch_otis_mock_aime","value":0.8861111111111111,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k2.7-code","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9555555555555556,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9833333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.6-plus","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9333333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_otis_mock_aime","value":0.8166666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.6-27b","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9111111111111111,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"epoch","metric":"epoch_otis_mock_aime","value":0.8888888888888888,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"epoch","metric":"epoch_otis_mock_aime","value":0.8666666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.6-flash","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9416666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.6-35b-a3b","source":"epoch","metric":"epoch_otis_mock_aime","value":0.8666666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.7-plus","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9333333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.7-flash","source":"epoch","metric":"epoch_otis_mock_aime","value":0.8666666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.6-flash","source":"epoch","metric":"epoch_otis_mock_aime","value":0.8444444444444444,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4-nano","source":"epoch","metric":"epoch_otis_mock_aime","value":0.8778,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"epoch","metric":"epoch_otis_mock_aime","value":0.8444444444444444,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_otis_mock_aime","value":0.8666666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemma-4-31b-it","source":"epoch","metric":"epoch_otis_mock_aime","value":0.7333333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_otis_mock_aime","value":0.956,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4-pro","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9666666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.6","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9444444444444444,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.5-flash-lite","source":"epoch","metric":"epoch_otis_mock_aime","value":0.7111111111111111,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.5-flash","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9555555555555556,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.1-flash-lite","source":"epoch","metric":"epoch_otis_mock_aime","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3-flash-preview","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9555555555555556,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-5","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9472222222222222,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9888888888888889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-4.6","source":"epoch","metric":"epoch_otis_mock_aime","value":0.857936507936508,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9833333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.7","source":"epoch","metric":"epoch_otis_mock_aime","value":0.978,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_otis_mock_aime","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"thinkingmachines/inkling","source":"epoch","metric":"epoch_otis_mock_aime","value":0.8888888888888888,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9444444444444444,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o3-mini","source":"epoch","metric":"epoch_otis_mock_aime","value":0.7694444444444445,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9138888888888889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-chat","source":"epoch","metric":"epoch_otis_mock_aime","value":0.4888888888888889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o1","source":"epoch","metric":"epoch_otis_mock_aime","value":0.7333333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9777777777777777,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5-nano","source":"epoch","metric":"epoch_otis_mock_aime","value":0.8111111111111111,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.2","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9611111111111111,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.5","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9777777777777777,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.3","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9333333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k2.6","source":"epoch","metric":"epoch_otis_mock_aime","value":0.9611111111111111,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5","source":"epoch","metric":"epoch_otis_mock_aime","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-4.7","source":"epoch","metric":"epoch_otis_mock_aime","value":0.8333333333333334,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-oss-120b","source":"epoch","metric":"epoch_otis_mock_aime","value":0.8888888888888888,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"epoch","metric":"epoch_otis_mock_aime","value":0.8666666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_otis_mock_aime","value":0.8611111111111112,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-2.5-pro","source":"epoch","metric":"epoch_otis_mock_aime","value":0.8472222222222222,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-4.5","source":"epoch","metric":"epoch_otis_mock_aime","value":0.7777777777777778,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-haiku-4.5","source":"epoch","metric":"epoch_otis_mock_aime","value":0.6666666666666666,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.1","source":"epoch","metric":"epoch_otis_mock_aime","value":0.6888888888888889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"epoch","metric":"epoch_otis_mock_aime","value":0.06944444444444445,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-r1-0528","source":"epoch","metric":"epoch_otis_mock_aime","value":0.6638888888888889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4.1-nano","source":"epoch","metric":"epoch_otis_mock_aime","value":0.28888888888888886,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4.1-mini","source":"epoch","metric":"epoch_otis_mock_aime","value":0.44722222222222224,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4.1","source":"epoch","metric":"epoch_otis_mock_aime","value":0.38333333333333336,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta-llama/llama-4-scout","source":"epoch","metric":"epoch_otis_mock_aime","value":0.07777777777777778,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen-plus","source":"epoch","metric":"epoch_otis_mock_aime","value":0.17777777777777778,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"epoch","metric":"epoch_otis_mock_aime","value":0.37777777777777777,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemma-2-27b-it","source":"epoch","metric":"epoch_otis_mock_aime","value":0.013888888888888888,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"epoch","metric":"epoch_otis_mock_aime","value":0.05138888888888889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4o-2024-08-06","source":"epoch","metric":"epoch_otis_mock_aime","value":0.06388888888888888,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"epoch","metric":"epoch_otis_mock_aime","value":0.08055555555555556,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4o-2024-05-13","source":"epoch","metric":"epoch_otis_mock_aime","value":0.0625,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"epoch","metric":"epoch_otis_mock_aime","value":0.03611111111111111,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"microsoft/phi-4","source":"epoch","metric":"epoch_otis_mock_aime","value":0.1375,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4o-2024-11-20","source":"epoch","metric":"epoch_otis_mock_aime","value":0.0625,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"mistralai/mistral-large-2407","source":"epoch","metric":"epoch_otis_mock_aime","value":0.08472222222222223,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-4-argon","source":"epoch","metric":"epoch_frontiermath","value":0.8596491228070176,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"mistralai/mistral-large-4-0","source":"epoch","metric":"epoch_frontiermath","value":0.5859649122807018,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"epoch","metric":"epoch_frontiermath","value":0.6736842105263158,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-haiku-5.5","source":"epoch","metric":"epoch_frontiermath","value":0.7508771929824561,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6.1-sol","source":"epoch","metric":"epoch_frontiermath","value":0.9368421052631579,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-5.5","source":"epoch","metric":"epoch_frontiermath","value":0.887719298245614,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-luna","source":"epoch","metric":"epoch_frontiermath","value":0.7894736842105263,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.7","source":"epoch","metric":"epoch_frontiermath","value":0.5298245614035088,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-sol","source":"epoch","metric":"epoch_frontiermath","value":0.8982456140350877,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-5.5","source":"epoch","metric":"epoch_frontiermath","value":0.9122807017543859,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta/muse-spark-1.3","source":"epoch","metric":"epoch_frontiermath","value":0.743859649122807,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.8-max-0902","source":"epoch","metric":"epoch_frontiermath","value":0.7473684210526316,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_frontiermath","value":0.6842105263157895,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-fable-5.1","source":"epoch","metric":"epoch_frontiermath","value":0.9017543859649123,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.1-flash-lite","source":"epoch","metric":"epoch_frontiermath","value":0.2771929824561403,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.6-35b-a3b","source":"epoch","metric":"epoch_frontiermath","value":0.20350877192982456,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.6-plus","source":"epoch","metric":"epoch_frontiermath","value":0.3824561403508772,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"epoch","metric":"epoch_frontiermath","value":0.312280701754386,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_frontiermath","value":0.9368421052631579,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_frontiermath","value":0.592057761732852,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.7-flash","source":"epoch","metric":"epoch_frontiermath","value":0.19298245614035087,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_frontiermath","value":0.8210526315789474,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.7-plus","source":"epoch","metric":"epoch_frontiermath","value":0.34385964912280703,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.6-flash","source":"epoch","metric":"epoch_frontiermath","value":0.22456140350877193,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.6-27b","source":"epoch","metric":"epoch_frontiermath","value":0.3508771929824561,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.1","source":"epoch","metric":"epoch_frontiermath","value":0.3684210526315789,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4-nano","source":"epoch","metric":"epoch_frontiermath","value":0.44912280701754387,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4-mini","source":"epoch","metric":"epoch_frontiermath","value":0.512280701754386,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"epoch","metric":"epoch_frontiermath","value":0.1824561403508772,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o1","source":"epoch","metric":"epoch_frontiermath","value":0.14736842105263157,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_frontiermath","value":0.3333333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_frontiermath","value":0.5543859649122806,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4.1-mini","source":"epoch","metric":"epoch_frontiermath","value":0.06666666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"epoch","metric":"epoch_frontiermath","value":0.007017543859649123,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4.1","source":"epoch","metric":"epoch_frontiermath","value":0.05964912280701754,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4o-2024-08-06","source":"epoch","metric":"epoch_frontiermath","value":0.0035087719298245615,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_frontiermath","value":0.36140350877192984,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o3-mini","source":"epoch","metric":"epoch_frontiermath","value":0.18596491228070175,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_frontiermath","value":0.4666666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5-nano","source":"epoch","metric":"epoch_frontiermath","value":0.2,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.3-flash","source":"epoch","metric":"epoch_frontiermath","value":0.5578947368421052,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.3","source":"epoch","metric":"epoch_frontiermath","value":0.6877192982456141,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"epoch","metric":"epoch_frontiermath","value":0.6456140350877193,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.7-flash","source":"epoch","metric":"epoch_frontiermath","value":0.7157894736842105,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"thinkingmachines/inkling-small","source":"epoch","metric":"epoch_frontiermath","value":0.4631578947368421,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_frontiermath","value":0.6596491228070176,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"thinkingmachines/inkling","source":"epoch","metric":"epoch_frontiermath","value":0.3333333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"epoch","metric":"epoch_frontiermath","value":0.5754385964912281,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.5-flash-lite","source":"epoch","metric":"epoch_frontiermath","value":0.2596491228070175,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.6-flash","source":"epoch","metric":"epoch_frontiermath","value":0.5894736842105263,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_frontiermath","value":0.856140350877193,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_frontiermath","value":0.721830985915493,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_frontiermath","value":0.8596491228070176,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_frontiermath","value":0.8912280701754386,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.5","source":"epoch","metric":"epoch_frontiermath","value":0.5719298245614035,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-5","source":"epoch","metric":"epoch_frontiermath","value":0.656140350877193,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.3","source":"epoch","metric":"epoch_frontiermath","value":0.4280701754385965,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4-pro","source":"epoch","metric":"epoch_frontiermath","value":0.45263157894736844,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.7-max","source":"epoch","metric":"epoch_frontiermath","value":0.6456140350877193,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4-pro","source":"epoch","metric":"epoch_frontiermath","value":0.8245614035087719,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.2-pro","source":"epoch","metric":"epoch_frontiermath","value":0.74,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k2.7-code","source":"epoch","metric":"epoch_frontiermath","value":0.5403508771929825,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.5-pro","source":"epoch","metric":"epoch_frontiermath","value":0.8771929824561403,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5-pro","source":"epoch","metric":"epoch_frontiermath","value":0.5578947368421052,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-2.5-pro","source":"epoch","metric":"epoch_frontiermath","value":0.24561403508771928,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3-flash-preview","source":"epoch","metric":"epoch_frontiermath","value":0.512280701754386,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_frontiermath","value":0.5964912280701754,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.1","source":"epoch","metric":"epoch_frontiermath","value":0.12631578947368421,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-4.5","source":"epoch","metric":"epoch_frontiermath","value":0.23859649122807017,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_frontiermath","value":0.7859649122807018,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_frontiermath","value":0.8526315789473684,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.2","source":"epoch","metric":"epoch_frontiermath","value":0.674,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_frontiermath","value":0.34385964912280703,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.6","source":"epoch","metric":"epoch_frontiermath","value":0.6596491228070176,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.7","source":"epoch","metric":"epoch_frontiermath","value":0.7017543859649122,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k2.6","source":"epoch","metric":"epoch_frontiermath","value":0.5719298245614035,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.5-flash","source":"epoch","metric":"epoch_frontiermath","value":0.6280701754385964,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_frontiermath","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_frontiermath","value":0.8701754385964913,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-4-argon","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.7804878048780488,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"mistralai/mistral-large-4-0","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.2682926829268293,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.2682926829268293,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-haiku-5.5","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.4634146341463415,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6.1-sol","source":"epoch","metric":"epoch_frontiermath_tier_4","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-5.5","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.8048780487804879,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-luna","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.5609756097560976,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.7","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.17073170731707318,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-sol","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.9,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-5.5","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.95,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta/muse-spark-1.3","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.4634146341463415,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.8-max-0902","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.4634146341463415,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.21951219512195122,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-fable-5.1","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.8780487804878049,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.976,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.3-flash","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.17073170731707318,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.3","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.2926829268292683,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.2682926829268293,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.7-flash","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.36585365853658536,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"thinkingmachines/inkling-small","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.17073170731707318,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.3170731707317073,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"thinkingmachines/inkling","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.04878048780487805,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.24390243902439024,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.5-flash-lite","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.6-flash","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.21951219512195122,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.7317073170731707,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.3902439024390244,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-sol-pro","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.8048780487804879,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.7073170731707317,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.6097560975609756,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.8292682926829268,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.5","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.24390243902439024,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-5","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.2926829268292683,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.2926829268292683,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.3","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.14634146341463414,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4-pro","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.024390243902439025,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.7-max","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.34146341463414637,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4-pro","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.5853658536585366,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.2-pro","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.46,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k2.7-code","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.12195121951219512,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.5-pro","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.7804878048780488,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5-pro","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.1951219512195122,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.12195121951219512,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4-nano","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.12195121951219512,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5-nano","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.024390243902439025,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4-mini","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.0975609756097561,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-2.5-pro","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3-flash-preview","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.17073170731707318,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.2682926829268293,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.1","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.024390243902439025,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-4.5","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.024390243902439025,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.49,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.725,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.2","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.317,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o3-mini","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.04878048780487805,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.04878048780487805,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.21951219512195122,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.6","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.2682926829268293,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.7","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.3170731707317073,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k2.6","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.2564102564102564,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.5-flash","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.2682926829268293,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.5609756097560976,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_frontiermath_tier_4","value":0.902,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-fable-5.1","source":"epoch","metric":"epoch_proofbench","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-fable-5.1","source":"epoch","metric":"epoch_proofbench_cost_usd","value":2.70347,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-fable-5.1","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":478.303,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-opus-5.5","source":"epoch","metric":"epoch_proofbench","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-opus-5.5","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.961648,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-opus-5.5","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":351.035,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-sonnet-5.5","source":"epoch","metric":"epoch_proofbench","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-sonnet-5.5","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.558327,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-sonnet-5.5","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":347.583,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_proofbench","value":0.99,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_proofbench_cost_usd","value":2.10619,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":590.886,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_proofbench","value":0.99,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_proofbench_cost_usd","value":1.71238,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":307.867,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-6.1-sol","source":"epoch","metric":"epoch_proofbench","value":0.99,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-6.1-sol","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.233057,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-6.1-sol","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":284.697,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"google/gemini-4-argon","source":"epoch","metric":"epoch_proofbench","value":0.99,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"google/gemini-4-argon","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.782978,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"google/gemini-4-argon","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":380.246,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_proofbench","value":0.9500000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_proofbench_cost_usd","value":5.451518,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":822.739,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-haiku-5.5","source":"epoch","metric":"epoch_proofbench","value":0.89,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-haiku-5.5","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.173874,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-haiku-5.5","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":418.047,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_proofbench","value":0.87,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_proofbench_cost_usd","value":1.646802,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":2070.511,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"meta/muse-wonder","source":"epoch","metric":"epoch_proofbench","value":0.84,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"meta/muse-wonder","source":"epoch","metric":"epoch_proofbench_cost_usd","value":1.313345,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"meta/muse-wonder","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":929.053,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_proofbench","value":0.8300000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_proofbench_cost_usd","value":1.438313,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":520.405,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-6-sol","source":"epoch","metric":"epoch_proofbench","value":0.8300000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-6-sol","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.476321,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-6-sol","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":304.509,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-sonnet-5","source":"epoch","metric":"epoch_proofbench","value":0.77,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-sonnet-5","source":"epoch","metric":"epoch_proofbench_cost_usd","value":1.373684,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-sonnet-5","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":898.079,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"tencent/hy4-preview","source":"epoch","metric":"epoch_proofbench","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"tencent/hy4-preview","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.335717,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"tencent/hy4-preview","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":1373.837,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_proofbench","value":0.74,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_proofbench_cost_usd","value":1.274209,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":777.341,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"epoch","metric":"epoch_proofbench","value":0.7000000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.24535,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":3693.469,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_proofbench","value":0.6900000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_proofbench_cost_usd","value":2.293129,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":1166.322,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-6-luna","source":"epoch","metric":"epoch_proofbench","value":0.64,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-6-luna","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.041637,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-6-luna","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":451.481,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"epoch","metric":"epoch_proofbench","value":0.63,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.123277,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":3769.808,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_proofbench","value":0.6,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.123288,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":513.687,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"google/gemini-3.7-flash","source":"epoch","metric":"epoch_proofbench","value":0.58,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"google/gemini-3.7-flash","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.558508,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"google/gemini-3.7-flash","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":423.698,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"qwen/qwen3.8-max-0902","source":"epoch","metric":"epoch_proofbench","value":0.58,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"qwen/qwen3.8-max-0902","source":"epoch","metric":"epoch_proofbench_cost_usd","value":1.503984,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"qwen/qwen3.8-max-0902","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":1867.622,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"meta/muse-spark-1.3","source":"epoch","metric":"epoch_proofbench","value":0.58,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"meta/muse-spark-1.3","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.479019,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"meta/muse-spark-1.3","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":568.696,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_proofbench","value":0.56,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_proofbench_cost_usd","value":3.202015,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":2751.526,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"epoch","metric":"epoch_proofbench","value":0.56,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.036568,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":933.981,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-opus-4.7","source":"epoch","metric":"epoch_proofbench","value":0.54,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-opus-4.7","source":"epoch","metric":"epoch_proofbench_cost_usd","value":1.807786,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-opus-4.7","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":679.708,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"epoch","metric":"epoch_proofbench","value":0.54,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.126437,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":546.595,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_proofbench","value":0.51,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.759043,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":861.898,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_proofbench","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_proofbench_cost_usd","value":1.68179,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":2953.443,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-opus-4.6","source":"epoch","metric":"epoch_proofbench","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-opus-4.6","source":"epoch","metric":"epoch_proofbench_cost_usd","value":2.703583,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-opus-4.6","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":3973.892,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"epoch","metric":"epoch_proofbench","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.062191,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":732.365,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"z-ai/glm-5.3","source":"epoch","metric":"epoch_proofbench","value":0.49,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"z-ai/glm-5.3","source":"epoch","metric":"epoch_proofbench_cost_usd","value":2.081538,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"z-ai/glm-5.3","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":2542.672,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_proofbench","value":0.48,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.602872,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":368.648,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-sonnet-4.6","source":"epoch","metric":"epoch_proofbench","value":0.45,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-sonnet-4.6","source":"epoch","metric":"epoch_proofbench_cost_usd","value":2.162108,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-sonnet-4.6","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":5463.593,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"meta/muse-spark-1.2","source":"epoch","metric":"epoch_proofbench","value":0.43,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"meta/muse-spark-1.2","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.442007,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"meta/muse-spark-1.2","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":469.146,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"stepfun/step-5-preview","source":"epoch","metric":"epoch_proofbench","value":0.42,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"stepfun/step-5-preview","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.714564,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"stepfun/step-5-preview","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":2313.592,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"meta/muse-spark-1.1","source":"epoch","metric":"epoch_proofbench","value":0.39,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"meta/muse-spark-1.1","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.519718,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"meta/muse-spark-1.1","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":1056.902,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_proofbench","value":0.36,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_proofbench_cost_usd","value":1.267043,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":3757.671,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"google/gemini-3.6-flash","source":"epoch","metric":"epoch_proofbench","value":0.36,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"google/gemini-3.6-flash","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.522059,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"google/gemini-3.6-flash","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":346.937,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_proofbench","value":0.35000000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":0,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"x-ai/grok-4.5","source":"epoch","metric":"epoch_proofbench","value":0.31,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"x-ai/grok-4.5","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.573991,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"x-ai/grok-4.5","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":668.86,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"google/gemini-3.5-flash","source":"epoch","metric":"epoch_proofbench","value":0.31,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"google/gemini-3.5-flash","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.569863,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"google/gemini-3.5-flash","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":394.476,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"qwen/qwen3.7-max","source":"epoch","metric":"epoch_proofbench","value":0.26,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"qwen/qwen3.7-max","source":"epoch","metric":"epoch_proofbench_cost_usd","value":2.462069,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"qwen/qwen3.7-max","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":771.408,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_proofbench","value":0.26,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.784253,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":889.059,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"x-ai/grok-4.7","source":"epoch","metric":"epoch_proofbench","value":0.26,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"x-ai/grok-4.7","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.787951,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"x-ai/grok-4.7","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":767.177,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"z-ai/glm-5.1","source":"epoch","metric":"epoch_proofbench","value":0.22222000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"z-ai/glm-5.1","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.584577,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"z-ai/glm-5.1","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":4755.746,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"epoch","metric":"epoch_proofbench","value":0.22,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.089853,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":1177.352,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5.4-mini","source":"epoch","metric":"epoch_proofbench","value":0.21,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5.4-mini","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.249441,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5.4-mini","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":1410.671,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"z-ai/glm-5.3-flash","source":"epoch","metric":"epoch_proofbench","value":0.21,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"z-ai/glm-5.3-flash","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.224234,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"z-ai/glm-5.3-flash","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":4274.803,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-sonnet-4.5","source":"epoch","metric":"epoch_proofbench","value":0.19,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-sonnet-4.5","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.65341,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"anthropic/claude-sonnet-4.5","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":12300.813,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"minimax/minimax-m3","source":"epoch","metric":"epoch_proofbench","value":0.18,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"minimax/minimax-m3","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.419224,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"minimax/minimax-m3","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":718.66,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_proofbench","value":0.18,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.852361,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":4579.325,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"moonshotai/kimi-k2.6","source":"epoch","metric":"epoch_proofbench","value":0.16,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"moonshotai/kimi-k2.6","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.295811,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"moonshotai/kimi-k2.6","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":1386.754,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"xiaomi/mimo-v2.5","source":"epoch","metric":"epoch_proofbench","value":0.16,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"xiaomi/mimo-v2.5","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.05707,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"xiaomi/mimo-v2.5","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":1255.813,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"deepseek/deepseek-v4-pro","source":"epoch","metric":"epoch_proofbench","value":0.16,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"deepseek/deepseek-v4-pro","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.033594,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"deepseek/deepseek-v4-pro","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":423.45,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"qwen/qwen3.8-27b","source":"epoch","metric":"epoch_proofbench","value":0.16,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"qwen/qwen3.8-27b","source":"epoch","metric":"epoch_proofbench_cost_usd","value":2.298832,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"qwen/qwen3.8-27b","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":1453.872,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"google/gemini-3-flash-preview","source":"epoch","metric":"epoch_proofbench","value":0.15,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"google/gemini-3-flash-preview","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.327286,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"google/gemini-3-flash-preview","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":1141.548,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5.2","source":"epoch","metric":"epoch_proofbench","value":0.15,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5.2","source":"epoch","metric":"epoch_proofbench_cost_usd","value":1.059689,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5.2","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":1493.817,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"google/gemini-3.5-flash-lite","source":"epoch","metric":"epoch_proofbench","value":0.13,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"google/gemini-3.5-flash-lite","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.132788,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"google/gemini-3.5-flash-lite","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":290.614,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5-nano","source":"epoch","metric":"epoch_proofbench","value":0.12,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5-nano","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.049218,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5-nano","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":3729.837,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"x-ai/grok-4.3","source":"epoch","metric":"epoch_proofbench","value":0.11,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"x-ai/grok-4.3","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.244122,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"x-ai/grok-4.3","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":1643.019,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"mistralai/mistral-large-4-0","source":"epoch","metric":"epoch_proofbench","value":0.1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"mistralai/mistral-large-4-0","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.642365,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"mistralai/mistral-large-4-0","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":1258.806,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_proofbench","value":0.09,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.22021,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":3349.817,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5.1-codex-max","source":"epoch","metric":"epoch_proofbench","value":0.09,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5.1-codex-max","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.527356,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5.1-codex-max","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":3184.213,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"mistralai/mistral-medium-3-5","source":"epoch","metric":"epoch_proofbench","value":0.09,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"mistralai/mistral-medium-3-5","source":"epoch","metric":"epoch_proofbench_cost_usd","value":1.302032,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"mistralai/mistral-medium-3-5","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":479.048,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"z-ai/glm-4.7","source":"epoch","metric":"epoch_proofbench","value":0.06,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"z-ai/glm-4.7","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.14404,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"z-ai/glm-4.7","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":3364.789,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"thinkingmachines/inkling-small","source":"epoch","metric":"epoch_proofbench","value":0.06,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"thinkingmachines/inkling-small","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.075386,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"thinkingmachines/inkling-small","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":507.301,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5.4-nano","source":"epoch","metric":"epoch_proofbench","value":0.05,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5.4-nano","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.015894,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5.4-nano","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":525.432,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"minimax/minimax-m2.5","source":"epoch","metric":"epoch_proofbench","value":0.04,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"minimax/minimax-m2.5","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.057497,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"minimax/minimax-m2.5","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":4514.143,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"minimax/minimax-m2.7","source":"epoch","metric":"epoch_proofbench","value":0.03,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"minimax/minimax-m2.7","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.04293,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"minimax/minimax-m2.7","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":1634.068,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"inception/mercury-2.5","source":"epoch","metric":"epoch_proofbench","value":0.03,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"inception/mercury-2.5","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.044105,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"inception/mercury-2.5","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":201.725,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"epoch","metric":"epoch_proofbench","value":0.02,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":2552.288,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"thinkingmachines/inkling","source":"epoch","metric":"epoch_proofbench","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"thinkingmachines/inkling","source":"epoch","metric":"epoch_proofbench_cost_usd","value":0.201396,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"thinkingmachines/inkling","source":"epoch","metric":"epoch_proofbench_latency_seconds","value":436.43,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/proof_bench"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_math_level_5","value":0.9784743202416919,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_math_level_5","value":0.9813066465256798,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-haiku-4.5","source":"epoch","metric":"epoch_math_level_5","value":0.9636087945413192,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-4.5","source":"epoch","metric":"epoch_math_level_5","value":0.9773413897280967,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5-nano","source":"epoch","metric":"epoch_math_level_5","value":0.952416918429003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-r1-0528","source":"epoch","metric":"epoch_math_level_5","value":0.9663897280966768,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_math_level_5","value":0.978285498489426,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_math_level_5","value":0.9777190332326284,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4.1-mini","source":"epoch","metric":"epoch_math_level_5","value":0.8729229607250756,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4.1-nano","source":"epoch","metric":"epoch_math_level_5","value":0.6999622356495468,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4.1","source":"epoch","metric":"epoch_math_level_5","value":0.8300604229607251,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta-llama/llama-4-scout","source":"epoch","metric":"epoch_math_level_5","value":0.6227341389728097,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen-plus","source":"epoch","metric":"epoch_math_level_5","value":0.6527567975830816,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"epoch","metric":"epoch_math_level_5","value":0.75547583081571,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemma-3-27b-it","source":"epoch","metric":"epoch_math_level_5","value":0.740370090634441,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o1","source":"epoch","metric":"epoch_math_level_5","value":0.947129909365559,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o3-mini","source":"epoch","metric":"epoch_math_level_5","value":0.9648791540785498,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4o-2024-11-20","source":"epoch","metric":"epoch_math_level_5","value":0.49773413897280966,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"microsoft/phi-4","source":"epoch","metric":"epoch_math_level_5","value":0.6493580060422961,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"epoch","metric":"epoch_math_level_5","value":0.22875755287009064,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"epoch","metric":"epoch_math_level_5","value":0.36678625377643503,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4o-2024-05-13","source":"epoch","metric":"epoch_math_level_5","value":0.5104796072507553,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"epoch","metric":"epoch_math_level_5","value":0.5263406344410876,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4o-2024-08-06","source":"epoch","metric":"epoch_math_level_5","value":0.5327605740181269,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemma-2-27b-it","source":"epoch","metric":"epoch_math_level_5","value":0.2788897280966767,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"mistralai/mistral-large-2407","source":"epoch","metric":"epoch_math_level_5","value":0.4481684290030212,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"epoch","metric":"epoch_math_level_5","value":0.41597432024169184,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"epoch","metric":"epoch_math_level_5","value":0.631703172205438,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-3.5-turbo-0613","source":"epoch","metric":"epoch_gsm8k","value":0.469,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://crfm.stanford.edu/helm/classic/latest/#/groups/gsm"},{"modelId":"openai/gpt-4","source":"epoch","metric":"epoch_gsm8k","value":0.92,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"http://arxiv.org/abs/2403.04652"},{"modelId":"openai/gpt-3.5-turbo","source":"epoch","metric":"epoch_gsm8k","value":0.5777,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"http://arxiv.org/abs/2309.10305"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"epoch","metric":"epoch_gsm8k","value":0.824,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"http://arxiv.org/abs/2404.14219"},{"modelId":"openai/gpt-4o-mini","source":"epoch","metric":"epoch_gsm8k","value":0.913,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"http://arxiv.org/abs/2404.14219"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"epoch","metric":"epoch_gsm8k","value":0.93,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"http://arxiv.org/abs/2409.12186"},{"modelId":"google/gemini-4-argon","source":"epoch","metric":"epoch_simpleqa_verified","value":0.76,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"epoch","metric":"epoch_simpleqa_verified","value":0.429,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-haiku-5.5","source":"epoch","metric":"epoch_simpleqa_verified","value":0.238,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"mistralai/mistral-large-4-0","source":"epoch","metric":"epoch_simpleqa_verified","value":0.2,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6.1-sol","source":"epoch","metric":"epoch_simpleqa_verified","value":0.739,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-5.5","source":"epoch","metric":"epoch_simpleqa_verified","value":0.465,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-luna","source":"epoch","metric":"epoch_simpleqa_verified","value":0.414,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.7","source":"epoch","metric":"epoch_simpleqa_verified","value":0.56,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-sol","source":"epoch","metric":"epoch_simpleqa_verified","value":0.607,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-5.5","source":"epoch","metric":"epoch_simpleqa_verified","value":0.722,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.8-max-0902","source":"epoch","metric":"epoch_simpleqa_verified","value":0.473,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_simpleqa_verified","value":0.697,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-fable-5.1","source":"epoch","metric":"epoch_simpleqa_verified","value":0.708,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"epoch","metric":"epoch_simpleqa_verified","value":0.083,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4o-2024-08-06","source":"epoch","metric":"epoch_simpleqa_verified","value":0.26,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4.1-nano","source":"epoch","metric":"epoch_simpleqa_verified","value":0.06,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4.1-mini","source":"epoch","metric":"epoch_simpleqa_verified","value":0.127,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4.1","source":"epoch","metric":"epoch_simpleqa_verified","value":0.311,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o3-mini","source":"epoch","metric":"epoch_simpleqa_verified","value":0.153,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o1","source":"epoch","metric":"epoch_simpleqa_verified","value":0.411,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta/muse-spark-1.1","source":"epoch","metric":"epoch_simpleqa_verified","value":0.5778894472361809,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_simpleqa_verified","value":0.756,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.3","source":"epoch","metric":"epoch_simpleqa_verified","value":0.41,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"epoch","metric":"epoch_simpleqa_verified","value":0.2535070140280561,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"meta/muse-spark-1.2","source":"epoch","metric":"epoch_simpleqa_verified","value":0.6030150753768844,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"thinkingmachines/inkling","source":"epoch","metric":"epoch_simpleqa_verified","value":0.403,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"epoch","metric":"epoch_simpleqa_verified","value":0.4044044044044044,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.1","source":"epoch","metric":"epoch_simpleqa_verified","value":0.34,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"thinkingmachines/inkling-small","source":"epoch","metric":"epoch_simpleqa_verified","value":0.191,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_simpleqa_verified","value":0.506,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_simpleqa_verified","value":0.342,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k2.7-code","source":"epoch","metric":"epoch_simpleqa_verified","value":0.365,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-4.7","source":"epoch","metric":"epoch_simpleqa_verified","value":0.322,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k2.5","source":"epoch","metric":"epoch_simpleqa_verified","value":0.343,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.7-max","source":"epoch","metric":"epoch_simpleqa_verified","value":0.5576730190571715,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.6-plus","source":"epoch","metric":"epoch_simpleqa_verified","value":0.44144144144144143,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.6-flash","source":"epoch","metric":"epoch_simpleqa_verified","value":0.15915915915915915,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"epoch","metric":"epoch_simpleqa_verified","value":0.2032032032032032,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.5-flash","source":"epoch","metric":"epoch_simpleqa_verified","value":0.662,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4-pro","source":"epoch","metric":"epoch_simpleqa_verified","value":0.46993987975951906,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.7-flash","source":"epoch","metric":"epoch_simpleqa_verified","value":0.692,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"epoch","metric":"epoch_simpleqa_verified","value":0.5290581162324649,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"epoch","metric":"epoch_simpleqa_verified","value":0.33633633633633636,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.6-flash","source":"epoch","metric":"epoch_simpleqa_verified","value":0.662,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemma-4-31b-it","source":"epoch","metric":"epoch_simpleqa_verified","value":0.104,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3-flash-preview","source":"epoch","metric":"epoch_simpleqa_verified","value":0.668,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_simpleqa_verified","value":0.493,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.3","source":"epoch","metric":"epoch_simpleqa_verified","value":0.332,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.5","source":"epoch","metric":"epoch_simpleqa_verified","value":0.483,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_simpleqa_verified","value":0.196,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.2","source":"epoch","metric":"epoch_simpleqa_verified","value":0.371,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_simpleqa_verified","value":0.494,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4-nano","source":"epoch","metric":"epoch_simpleqa_verified","value":0.117,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_simpleqa_verified","value":0.501,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4-mini","source":"epoch","metric":"epoch_simpleqa_verified","value":0.294,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_simpleqa_verified","value":0.63,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4-pro","source":"epoch","metric":"epoch_simpleqa_verified","value":0.463,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.1","source":"epoch","metric":"epoch_simpleqa_verified","value":0.48,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-4.5","source":"epoch","metric":"epoch_simpleqa_verified","value":0.307,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_simpleqa_verified","value":0.451,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-5","source":"epoch","metric":"epoch_simpleqa_verified","value":0.337,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_simpleqa_verified","value":0.457,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-haiku-4.5","source":"epoch","metric":"epoch_simpleqa_verified","value":0.132,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.6","source":"epoch","metric":"epoch_simpleqa_verified","value":0.47,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-4.6","source":"epoch","metric":"epoch_simpleqa_verified","value":0.355,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.7","source":"epoch","metric":"epoch_simpleqa_verified","value":0.517,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_simpleqa_verified","value":0.53,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_simpleqa_verified","value":0.697,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_simpleqa_verified","value":0.432,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_simpleqa_verified","value":0.41,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_simpleqa_verified","value":0.599,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_simpleqa_verified","value":0.707,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_simpleqa_verified","value":0.735,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k2.6","source":"epoch","metric":"epoch_simpleqa_verified","value":0.349,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_simpleqa_verified","value":0.216,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5-nano","source":"epoch","metric":"epoch_simpleqa_verified","value":0.117,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"amazon/nova-lite-v1","source":"epoch","metric":"epoch_mmlu","value":0.77,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},{"modelId":"amazon/nova-micro-v1","source":"epoch","metric":"epoch_mmlu","value":0.708,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},{"modelId":"amazon/nova-pro-v1","source":"epoch","metric":"epoch_mmlu","value":0.82,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},{"modelId":"google/gemma-2-27b-it","source":"epoch","metric":"epoch_mmlu","value":0.757,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},{"modelId":"openai/gpt-4o-mini","source":"epoch","metric":"epoch_mmlu","value":0.818,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"http://arxiv.org/abs/2412.08905"},{"modelId":"openai/gpt-3.5-turbo","source":"epoch","metric":"epoch_mmlu","value":0.6854,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"http://arxiv.org/abs/2309.10305"},{"modelId":"openai/gpt-3.5-turbo-0613","source":"epoch","metric":"epoch_mmlu","value":0.689,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},{"modelId":"openai/gpt-4","source":"epoch","metric":"epoch_mmlu","value":0.864,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arxiv.org/pdf/2303.08774"},{"modelId":"openai/gpt-4-turbo","source":"epoch","metric":"epoch_mmlu","value":0.813,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},{"modelId":"openai/gpt-4o","source":"epoch","metric":"epoch_mmlu","value":0.881,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"http://arxiv.org/abs/2412.08905"},{"modelId":"openai/gpt-4o-2024-05-13","source":"epoch","metric":"epoch_mmlu","value":0.842,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},{"modelId":"openai/gpt-4o-2024-08-06","source":"epoch","metric":"epoch_mmlu","value":0.843,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"epoch","metric":"epoch_mmlu","value":0.767,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"epoch","metric":"epoch_mmlu","value":0.561,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"epoch","metric":"epoch_mmlu","value":0.801,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"epoch","metric":"epoch_mmlu","value":0.863,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"http://arxiv.org/abs/2412.08905"},{"modelId":"mistralai/mistral-large","source":"epoch","metric":"epoch_mmlu","value":0.688,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},{"modelId":"mistralai/mistral-large-2407","source":"epoch","metric":"epoch_mmlu","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},{"modelId":"mistralai/mistral-nemo","source":"epoch","metric":"epoch_mmlu","value":0.653,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},{"modelId":"microsoft/phi-4","source":"epoch","metric":"epoch_mmlu","value":0.848,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"http://arxiv.org/abs/2412.08905"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"epoch","metric":"epoch_mmlu","value":0.853,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"http://arxiv.org/abs/2412.08905"},{"modelId":"qwen/qwen-2.5-7b-instruct","source":"epoch","metric":"epoch_mmlu","value":0.729,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://crfm.stanford.edu/helm/lite/latest/#/leaderboard/mmlu"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"epoch","metric":"epoch_mmlu","value":0.791,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"http://arxiv.org/abs/2409.12186"},{"modelId":"google/gemini-3-flash-preview","source":"epoch","metric":"epoch_geobench","value":0.88,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_geobench","value":0.81,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://geobench.org/"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_geobench","value":0.74,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://geobench.org/"},{"modelId":"openai/o1","source":"epoch","metric":"epoch_geobench","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://geobench.org/"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_geobench","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-4.1","source":"epoch","metric":"epoch_geobench","value":0.72,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://geobench.org/"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_geobench","value":0.64,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://geobench.org/"},{"modelId":"openai/gpt-4o-2024-11-20","source":"epoch","metric":"epoch_geobench","value":0.71,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://geobench.org/"},{"modelId":"qwen/qwen2.5-vl-72b-instruct","source":"epoch","metric":"epoch_geobench","value":0.62,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://geobench.org/"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"epoch","metric":"epoch_geobench","value":0.64,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://geobench.org/"},{"modelId":"google/gemma-3-27b-it","source":"epoch","metric":"epoch_geobench","value":0.52,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://geobench.org/"},{"modelId":"meta-llama/llama-4-maverick","source":"epoch","metric":"epoch_geobench","value":0.52,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://geobench.org/"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_dtbench","value":0.9787,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_dtbench","value":0.9840000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"openai/gpt-5.6-sol-pro","source":"epoch","metric":"epoch_dtbench","value":0.96,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_dtbench","value":0.9573,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_dtbench","value":0.9493,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_dtbench","value":0.96,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"anthropic/claude-opus-4.6","source":"epoch","metric":"epoch_dtbench","value":0.912,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"openai/gpt-5.5-pro","source":"epoch","metric":"epoch_dtbench","value":0.96,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"anthropic/claude-opus-4.7","source":"epoch","metric":"epoch_dtbench","value":0.9465000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_dtbench","value":0.9440000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"google/gemini-3.7-flash","source":"epoch","metric":"epoch_dtbench","value":0.968,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_dtbench","value":0.9707,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"meta/muse-spark-1.1","source":"epoch","metric":"epoch_dtbench","value":0.9440000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_dtbench","value":0.9333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_dtbench","value":0.912,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"meta/muse-spark-1.2","source":"epoch","metric":"epoch_dtbench","value":0.9467,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_dtbench","value":0.9733,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"anthropic/claude-sonnet-5","source":"epoch","metric":"epoch_dtbench","value":0.9248000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"x-ai/grok-4.5","source":"epoch","metric":"epoch_dtbench","value":0.9653,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"google/gemini-3.5-flash","source":"epoch","metric":"epoch_dtbench","value":0.9467,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"google/gemini-3.6-flash","source":"epoch","metric":"epoch_dtbench","value":0.9547,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"qwen/qwen3.8-max-0902","source":"epoch","metric":"epoch_dtbench","value":0.92,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"anthropic/claude-sonnet-4.6","source":"epoch","metric":"epoch_dtbench","value":0.8987,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"openai/gpt-5.2","source":"epoch","metric":"epoch_dtbench","value":0.9093000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_dtbench","value":0.8987,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_dtbench","value":0.8906999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_dtbench","value":0.9359999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"openai/gpt-5.1","source":"epoch","metric":"epoch_dtbench","value":0.9013,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"qwen/qwen3.7-max","source":"epoch","metric":"epoch_dtbench","value":0.9227,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"google/gemini-3-flash-preview","source":"epoch","metric":"epoch_dtbench","value":0.8906999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"deepseek/deepseek-v4-pro","source":"epoch","metric":"epoch_dtbench","value":0.9067000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_dtbench","value":0.9067000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"epoch","metric":"epoch_dtbench","value":0.9093000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"x-ai/grok-4.20","source":"epoch","metric":"epoch_dtbench","value":0.9013,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"moonshotai/kimi-k2.6","source":"epoch","metric":"epoch_dtbench","value":0.9093000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"openai/o3-pro","source":"epoch","metric":"epoch_dtbench","value":0.8693000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_dtbench","value":0.848,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"x-ai/grok-4.3","source":"epoch","metric":"epoch_dtbench","value":0.9067000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"thinkingmachines/inkling","source":"epoch","metric":"epoch_dtbench","value":0.8747,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"openai/gpt-5.4-mini","source":"epoch","metric":"epoch_dtbench","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"anthropic/claude-sonnet-4.5","source":"epoch","metric":"epoch_dtbench","value":0.8320000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"epoch","metric":"epoch_dtbench","value":0.9013,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"google/gemini-3.5-flash-lite","source":"epoch","metric":"epoch_dtbench","value":0.8347,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"google/gemma-4-31b-it","source":"epoch","metric":"epoch_dtbench","value":0.8267,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"epoch","metric":"epoch_dtbench","value":0.8747,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"qwen/qwen3.7-plus","source":"epoch","metric":"epoch_dtbench","value":0.84,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"openai/gpt-5.4-nano","source":"epoch","metric":"epoch_dtbench","value":0.8027,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"deepseek/deepseek-v4-flash","source":"epoch","metric":"epoch_dtbench","value":0.8640000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_dtbench","value":0.8053,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"anthropic/claude-opus-4.1","source":"epoch","metric":"epoch_dtbench","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"google/gemini-2.5-pro","source":"epoch","metric":"epoch_dtbench","value":0.8240000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"qwen/qwen3.5-27b","source":"epoch","metric":"epoch_dtbench","value":0.8240000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"epoch","metric":"epoch_dtbench","value":0.8053,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"minimax/minimax-m3","source":"epoch","metric":"epoch_dtbench","value":0.7893000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"google/gemini-3.1-flash-lite","source":"epoch","metric":"epoch_dtbench","value":0.768,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"epoch","metric":"epoch_dtbench","value":0.8773000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"epoch","metric":"epoch_dtbench","value":0.8427,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"qwen/qwen3.6-plus","source":"epoch","metric":"epoch_dtbench","value":0.8187000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"deepseek/deepseek-v3.2","source":"epoch","metric":"epoch_dtbench","value":0.856,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"qwen/qwen3.6-27b","source":"epoch","metric":"epoch_dtbench","value":0.7813,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"epoch","metric":"epoch_dtbench","value":0.8453,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"qwen/qwen3.6-flash","source":"epoch","metric":"epoch_dtbench","value":0.7706999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"anthropic/claude-haiku-4.5","source":"epoch","metric":"epoch_dtbench","value":0.736,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"epoch","metric":"epoch_dtbench","value":0.8027,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"epoch","metric":"epoch_dtbench","value":0.8293,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"epoch","metric":"epoch_dtbench","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"epoch","metric":"epoch_dtbench","value":0.8133,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"qwen/qwen-plus","source":"epoch","metric":"epoch_dtbench","value":0.8107,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_dtbench","value":0.7759999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"google/gemma-4-26b-a4b-it","source":"epoch","metric":"epoch_dtbench","value":0.7493000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"deepseek/deepseek-chat-v3.1","source":"epoch","metric":"epoch_dtbench","value":0.8267,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"qwen/qwen3.6-35b-a3b","source":"epoch","metric":"epoch_dtbench","value":0.7387,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"openai/gpt-oss-120b","source":"epoch","metric":"epoch_dtbench","value":0.7626999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"epoch","metric":"epoch_dtbench","value":0.784,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"openai/o1","source":"epoch","metric":"epoch_dtbench","value":0.7467,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"google/gemini-2.5-flash","source":"epoch","metric":"epoch_dtbench","value":0.7653,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"mistralai/mistral-medium-3","source":"epoch","metric":"epoch_dtbench","value":0.6227,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"mistralai/mistral-medium-3-5","source":"epoch","metric":"epoch_dtbench","value":0.7547,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"openai/gpt-4.1","source":"epoch","metric":"epoch_dtbench","value":0.6827,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"mistralai/mistral-large-2407","source":"epoch","metric":"epoch_dtbench","value":0.6121,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"qwen/qwen3.5-9b","source":"epoch","metric":"epoch_dtbench","value":0.7120000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"mistralai/mistral-large","source":"epoch","metric":"epoch_dtbench","value":0.6082,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"openai/o3-mini","source":"epoch","metric":"epoch_dtbench","value":0.688,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"epoch","metric":"epoch_dtbench","value":0.672,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"openai/gpt-4.1-mini","source":"epoch","metric":"epoch_dtbench","value":0.688,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"mistralai/mistral-small-2603","source":"epoch","metric":"epoch_dtbench","value":0.7093,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"openai/gpt-oss-20b","source":"epoch","metric":"epoch_dtbench","value":0.68,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"qwen/qwen3-32b","source":"epoch","metric":"epoch_dtbench","value":0.6747,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"qwen/qwen3-14b","source":"epoch","metric":"epoch_dtbench","value":0.64,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"mistralai/mistral-medium-3.1","source":"epoch","metric":"epoch_dtbench","value":0.6747,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"mistralai/mistral-large-2512","source":"epoch","metric":"epoch_dtbench","value":0.6507,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"openai/gpt-4o","source":"epoch","metric":"epoch_dtbench","value":0.6453,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"meta-llama/llama-4-maverick","source":"epoch","metric":"epoch_dtbench","value":0.6187,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"epoch","metric":"epoch_dtbench","value":0.648,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"epoch","metric":"epoch_dtbench","value":0.5947,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"openai/gpt-4","source":"epoch","metric":"epoch_dtbench","value":0.6267,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"qwen/qwen3-30b-a3b","source":"epoch","metric":"epoch_dtbench","value":0.6027,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"mistralai/mixtral-8x22b-instruct","source":"epoch","metric":"epoch_dtbench","value":0.5514,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"google/gemini-2.5-flash-lite","source":"epoch","metric":"epoch_dtbench","value":0.6283,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"deepseek/deepseek-chat","source":"epoch","metric":"epoch_dtbench","value":0.6267,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"epoch","metric":"epoch_dtbench","value":0.6,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"epoch","metric":"epoch_dtbench","value":0.6293,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"openai/gpt-5-nano","source":"epoch","metric":"epoch_dtbench","value":0.6267,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"meta-llama/llama-4-scout","source":"epoch","metric":"epoch_dtbench","value":0.5787,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"openai/gpt-4-turbo","source":"epoch","metric":"epoch_dtbench","value":0.616,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"cohere/command-a","source":"epoch","metric":"epoch_dtbench","value":0.6133,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"google/gemma-3-27b-it","source":"epoch","metric":"epoch_dtbench","value":0.5253,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"openai/gpt-4o-mini","source":"epoch","metric":"epoch_dtbench","value":0.544,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"mistralai/mistral-nemo","source":"epoch","metric":"epoch_dtbench","value":0.48610000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"epoch","metric":"epoch_dtbench","value":0.5093,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"google/gemma-3-12b-it","source":"epoch","metric":"epoch_dtbench","value":0.488,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"openai/gpt-3.5-turbo","source":"epoch","metric":"epoch_dtbench","value":0.4853,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"openai/gpt-4.1-nano","source":"epoch","metric":"epoch_dtbench","value":0.5253,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"qwen/qwen-2.5-7b-instruct","source":"epoch","metric":"epoch_dtbench","value":0.4773,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"google/gemma-3-4b-it","source":"epoch","metric":"epoch_dtbench","value":0.5093,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"google/gemma-2-27b-it","source":"epoch","metric":"epoch_dtbench","value":0.48,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"anthropic/claude-fable-5.1","source":"epoch","metric":"epoch_dtbench","value":0.976,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_dtbench","value":0.9733,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"meta/muse-spark-1.3","source":"epoch","metric":"epoch_dtbench","value":0.9653,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_dtbench","value":0.9572,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"z-ai/glm-5.3","source":"epoch","metric":"epoch_dtbench","value":0.8767,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"epoch","metric":"epoch_dtbench","value":0.9387000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"epoch","metric":"epoch_dtbench","value":0.8987,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"qwen/qwen3.8-27b","source":"epoch","metric":"epoch_dtbench","value":0.88,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"anthropic/claude-opus-5.5","source":"epoch","metric":"epoch_dtbench","value":0.9893000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"openai/gpt-6-sol","source":"epoch","metric":"epoch_dtbench","value":0.9733,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"openai/gpt-6-luna","source":"epoch","metric":"epoch_dtbench","value":0.9013,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"x-ai/grok-4.7","source":"epoch","metric":"epoch_dtbench","value":0.96,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"anthropic/claude-sonnet-5.5","source":"epoch","metric":"epoch_dtbench","value":0.9733,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"openai/gpt-6.1-sol","source":"epoch","metric":"epoch_dtbench","value":0.9653,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"google/gemini-4-argon","source":"epoch","metric":"epoch_dtbench","value":0.976,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"meta/muse-wonder","source":"epoch","metric":"epoch_dtbench","value":0.9520000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"anthropic/claude-haiku-5.5","source":"epoch","metric":"epoch_dtbench","value":0.9499,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"mistralai/mistral-large-4-0","source":"epoch","metric":"epoch_dtbench","value":0.8824,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/dtbench"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_lmca","value":0.6445000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_lmca","value":0.6115,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"openai/gpt-5.6-sol-pro","source":"epoch","metric":"epoch_lmca","value":0.5921000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_lmca","value":0.5849000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_lmca","value":0.5751,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_lmca","value":0.5427000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"anthropic/claude-opus-4.6","source":"epoch","metric":"epoch_lmca","value":0.5576,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"openai/gpt-5.5-pro","source":"epoch","metric":"epoch_lmca","value":0.5394,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"anthropic/claude-opus-4.7","source":"epoch","metric":"epoch_lmca","value":0.522,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_lmca","value":0.5197,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"google/gemini-3.7-flash","source":"epoch","metric":"epoch_lmca","value":0.5038,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_lmca","value":0.5382,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"meta/muse-spark-1.1","source":"epoch","metric":"epoch_lmca","value":0.4991,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_lmca","value":0.5495,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_lmca","value":0.5274,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"meta/muse-spark-1.2","source":"epoch","metric":"epoch_lmca","value":0.48350000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_lmca","value":0.48450000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"anthropic/claude-sonnet-5","source":"epoch","metric":"epoch_lmca","value":0.5002000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"x-ai/grok-4.5","source":"epoch","metric":"epoch_lmca","value":0.452,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"google/gemini-3.5-flash","source":"epoch","metric":"epoch_lmca","value":0.4715,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"google/gemini-3.6-flash","source":"epoch","metric":"epoch_lmca","value":0.44930000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"qwen/qwen3.8-max-0902","source":"epoch","metric":"epoch_lmca","value":0.46240000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"anthropic/claude-sonnet-4.6","source":"epoch","metric":"epoch_lmca","value":0.4651,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"openai/gpt-5.2","source":"epoch","metric":"epoch_lmca","value":0.4391,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_lmca","value":0.4446,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_lmca","value":0.4854,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_lmca","value":0.4582,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"openai/gpt-5.1","source":"epoch","metric":"epoch_lmca","value":0.4389,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"qwen/qwen3.7-max","source":"epoch","metric":"epoch_lmca","value":0.44020000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"google/gemini-3-flash-preview","source":"epoch","metric":"epoch_lmca","value":0.4313,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"deepseek/deepseek-v4-pro","source":"epoch","metric":"epoch_lmca","value":0.41200000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_lmca","value":0.39990000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"epoch","metric":"epoch_lmca","value":0.4173,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"x-ai/grok-4.20","source":"epoch","metric":"epoch_lmca","value":0.3866,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"moonshotai/kimi-k2.6","source":"epoch","metric":"epoch_lmca","value":0.3726,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"openai/o3-pro","source":"epoch","metric":"epoch_lmca","value":0.3848,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_lmca","value":0.397,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"x-ai/grok-4.3","source":"epoch","metric":"epoch_lmca","value":0.3833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"thinkingmachines/inkling","source":"epoch","metric":"epoch_lmca","value":0.37579999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"openai/gpt-5.4-mini","source":"epoch","metric":"epoch_lmca","value":0.4079,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"anthropic/claude-sonnet-4.5","source":"epoch","metric":"epoch_lmca","value":0.3876,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"epoch","metric":"epoch_lmca","value":0.369,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"google/gemini-3.5-flash-lite","source":"epoch","metric":"epoch_lmca","value":0.376,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"google/gemma-4-31b-it","source":"epoch","metric":"epoch_lmca","value":0.3925,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"epoch","metric":"epoch_lmca","value":0.3789,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"qwen/qwen3.7-plus","source":"epoch","metric":"epoch_lmca","value":0.37579999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"openai/gpt-5.4-nano","source":"epoch","metric":"epoch_lmca","value":0.3686,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"deepseek/deepseek-v4-flash","source":"epoch","metric":"epoch_lmca","value":0.3588,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_lmca","value":0.342,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"anthropic/claude-opus-4.1","source":"epoch","metric":"epoch_lmca","value":0.37079999999999996,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"google/gemini-2.5-pro","source":"epoch","metric":"epoch_lmca","value":0.34770000000000006,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"qwen/qwen3.5-27b","source":"epoch","metric":"epoch_lmca","value":0.3398,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"epoch","metric":"epoch_lmca","value":0.3636,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"minimax/minimax-m3","source":"epoch","metric":"epoch_lmca","value":0.337,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"google/gemini-3.1-flash-lite","source":"epoch","metric":"epoch_lmca","value":0.35009999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"epoch","metric":"epoch_lmca","value":0.2911,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"epoch","metric":"epoch_lmca","value":0.3223,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"qwen/qwen3.6-plus","source":"epoch","metric":"epoch_lmca","value":0.3309,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"deepseek/deepseek-v3.2","source":"epoch","metric":"epoch_lmca","value":0.2882,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"qwen/qwen3.6-27b","source":"epoch","metric":"epoch_lmca","value":0.3453,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"epoch","metric":"epoch_lmca","value":0.295,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"qwen/qwen3.6-flash","source":"epoch","metric":"epoch_lmca","value":0.3098,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"anthropic/claude-haiku-4.5","source":"epoch","metric":"epoch_lmca","value":0.3094,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"epoch","metric":"epoch_lmca","value":0.29309999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"epoch","metric":"epoch_lmca","value":0.2914,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"epoch","metric":"epoch_lmca","value":0.2947,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"epoch","metric":"epoch_lmca","value":0.2858,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"qwen/qwen-plus","source":"epoch","metric":"epoch_lmca","value":0.2396,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_lmca","value":0.265,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"google/gemma-4-26b-a4b-it","source":"epoch","metric":"epoch_lmca","value":0.2968,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"deepseek/deepseek-chat-v3.1","source":"epoch","metric":"epoch_lmca","value":0.2429,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"qwen/qwen3.6-35b-a3b","source":"epoch","metric":"epoch_lmca","value":0.297,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"openai/gpt-oss-120b","source":"epoch","metric":"epoch_lmca","value":0.2214,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"epoch","metric":"epoch_lmca","value":0.2352,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"openai/o1","source":"epoch","metric":"epoch_lmca","value":0.2227,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"google/gemini-2.5-flash","source":"epoch","metric":"epoch_lmca","value":0.2749,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"mistralai/mistral-medium-3-5","source":"epoch","metric":"epoch_lmca","value":0.2606,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"openai/gpt-4.1","source":"epoch","metric":"epoch_lmca","value":0.2561,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"qwen/qwen3.5-9b","source":"epoch","metric":"epoch_lmca","value":0.2447,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"openai/o3-mini","source":"epoch","metric":"epoch_lmca","value":0.18969999999999998,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"epoch","metric":"epoch_lmca","value":0.2237,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"openai/gpt-4.1-mini","source":"epoch","metric":"epoch_lmca","value":0.21120000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"mistralai/mistral-small-2603","source":"epoch","metric":"epoch_lmca","value":0.2061,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"openai/gpt-oss-20b","source":"epoch","metric":"epoch_lmca","value":0.1451,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"qwen/qwen3-32b","source":"epoch","metric":"epoch_lmca","value":0.1728,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"qwen/qwen3-14b","source":"epoch","metric":"epoch_lmca","value":0.1819,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"mistralai/mistral-medium-3.1","source":"epoch","metric":"epoch_lmca","value":0.1905,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"mistralai/mistral-large-2512","source":"epoch","metric":"epoch_lmca","value":0.167,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"openai/gpt-4o","source":"epoch","metric":"epoch_lmca","value":0.1659,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"meta-llama/llama-4-maverick","source":"epoch","metric":"epoch_lmca","value":0.1587,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"epoch","metric":"epoch_lmca","value":0.1547,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"epoch","metric":"epoch_lmca","value":0.1752,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"openai/gpt-4","source":"epoch","metric":"epoch_lmca","value":0.1706,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"qwen/qwen3-30b-a3b","source":"epoch","metric":"epoch_lmca","value":0.1582,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"google/gemini-2.5-flash-lite","source":"epoch","metric":"epoch_lmca","value":0.1807,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"deepseek/deepseek-chat","source":"epoch","metric":"epoch_lmca","value":0.1524,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"epoch","metric":"epoch_lmca","value":0.1485,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"epoch","metric":"epoch_lmca","value":0.1342,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"openai/gpt-5-nano","source":"epoch","metric":"epoch_lmca","value":0.0793,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"meta-llama/llama-4-scout","source":"epoch","metric":"epoch_lmca","value":0.11960000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"openai/gpt-4-turbo","source":"epoch","metric":"epoch_lmca","value":0.0978,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"cohere/command-a","source":"epoch","metric":"epoch_lmca","value":0.1028,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"google/gemma-3-27b-it","source":"epoch","metric":"epoch_lmca","value":0.12279999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"openai/gpt-4o-mini","source":"epoch","metric":"epoch_lmca","value":0.1037,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"epoch","metric":"epoch_lmca","value":0.053700000000000005,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"google/gemma-3-12b-it","source":"epoch","metric":"epoch_lmca","value":0.0446,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"openai/gpt-3.5-turbo","source":"epoch","metric":"epoch_lmca","value":0.0965,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"openai/gpt-4.1-nano","source":"epoch","metric":"epoch_lmca","value":0.0546,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"qwen/qwen-2.5-7b-instruct","source":"epoch","metric":"epoch_lmca","value":0.06420000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"google/gemma-3-4b-it","source":"epoch","metric":"epoch_lmca","value":0.0278,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"google/gemma-2-27b-it","source":"epoch","metric":"epoch_lmca","value":0.071,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"anthropic/claude-fable-5.1","source":"epoch","metric":"epoch_lmca","value":0.6546,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_lmca","value":0.6437,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"meta/muse-spark-1.3","source":"epoch","metric":"epoch_lmca","value":0.5387,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_lmca","value":0.529,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"z-ai/glm-5.3","source":"epoch","metric":"epoch_lmca","value":0.5551,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"epoch","metric":"epoch_lmca","value":0.4545,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"epoch","metric":"epoch_lmca","value":0.4697,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"qwen/qwen3.8-27b","source":"epoch","metric":"epoch_lmca","value":0.4136,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"anthropic/claude-opus-5.5","source":"epoch","metric":"epoch_lmca","value":0.6823,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"openai/gpt-6-sol","source":"epoch","metric":"epoch_lmca","value":0.5908,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"openai/gpt-6-luna","source":"epoch","metric":"epoch_lmca","value":0.4449,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"x-ai/grok-4.7","source":"epoch","metric":"epoch_lmca","value":0.4938,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"anthropic/claude-sonnet-5.5","source":"epoch","metric":"epoch_lmca","value":0.6826000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"openai/gpt-6.1-sol","source":"epoch","metric":"epoch_lmca","value":0.6278,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"google/gemini-4-argon","source":"epoch","metric":"epoch_lmca","value":0.6369,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"meta/muse-wonder","source":"epoch","metric":"epoch_lmca","value":0.5684,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"anthropic/claude-haiku-5.5","source":"epoch","metric":"epoch_lmca","value":0.5106,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"mistralai/mistral-large-4-0","source":"epoch","metric":"epoch_lmca","value":0.3579,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://conceptualreasoning.ai/lmca"},{"modelId":"deepseek/deepseek-r1-0528","source":"epoch","metric":"epoch_fiction_livebench","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"deepseek/deepseek-r1-0528","source":"epoch","metric":"epoch_fiction_livebench_at_0","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"deepseek/deepseek-r1-0528","source":"epoch","metric":"epoch_fiction_livebench_at_400","value":0.917,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"deepseek/deepseek-r1-0528","source":"epoch","metric":"epoch_fiction_livebench_at_1k","value":0.833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"deepseek/deepseek-r1-0528","source":"epoch","metric":"epoch_fiction_livebench_at_2k","value":0.829,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"deepseek/deepseek-r1-0528","source":"epoch","metric":"epoch_fiction_livebench_at_4k","value":0.889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"deepseek/deepseek-r1-0528","source":"epoch","metric":"epoch_fiction_livebench_at_8k","value":0.861,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"deepseek/deepseek-r1-0528","source":"epoch","metric":"epoch_fiction_livebench_at_32k","value":0.694,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"deepseek/deepseek-r1-0528","source":"epoch","metric":"epoch_fiction_livebench_at_60k","value":0.583,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-oss-120b","source":"epoch","metric":"epoch_fiction_livebench","value":0.444,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-oss-120b","source":"epoch","metric":"epoch_fiction_livebench_at_0","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-oss-120b","source":"epoch","metric":"epoch_fiction_livebench_at_400","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-oss-120b","source":"epoch","metric":"epoch_fiction_livebench_at_1k","value":0.611,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-oss-120b","source":"epoch","metric":"epoch_fiction_livebench_at_2k","value":0.556,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-oss-120b","source":"epoch","metric":"epoch_fiction_livebench_at_4k","value":0.472,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-oss-120b","source":"epoch","metric":"epoch_fiction_livebench_at_8k","value":0.444,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-oss-120b","source":"epoch","metric":"epoch_fiction_livebench_at_32k","value":0.389,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"meta-llama/llama-4-maverick","source":"epoch","metric":"epoch_fiction_livebench","value":0.462,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"meta-llama/llama-4-maverick","source":"epoch","metric":"epoch_fiction_livebench_at_0","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"meta-llama/llama-4-maverick","source":"epoch","metric":"epoch_fiction_livebench_at_400","value":0.56,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"meta-llama/llama-4-maverick","source":"epoch","metric":"epoch_fiction_livebench_at_1k","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"meta-llama/llama-4-maverick","source":"epoch","metric":"epoch_fiction_livebench_at_2k","value":0.52,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"meta-llama/llama-4-maverick","source":"epoch","metric":"epoch_fiction_livebench_at_4k","value":0.48,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"meta-llama/llama-4-maverick","source":"epoch","metric":"epoch_fiction_livebench_at_8k","value":0.48,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"meta-llama/llama-4-maverick","source":"epoch","metric":"epoch_fiction_livebench_at_32k","value":0.44,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"meta-llama/llama-4-maverick","source":"epoch","metric":"epoch_fiction_livebench_at_60k","value":0.32,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"meta-llama/llama-4-maverick","source":"epoch","metric":"epoch_fiction_livebench_at_120k","value":0.364,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"epoch","metric":"epoch_fiction_livebench","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"epoch","metric":"epoch_fiction_livebench_at_0","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"epoch","metric":"epoch_fiction_livebench_at_400","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"epoch","metric":"epoch_fiction_livebench_at_1k","value":0.917,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"epoch","metric":"epoch_fiction_livebench_at_2k","value":0.861,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"epoch","metric":"epoch_fiction_livebench_at_4k","value":0.917,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"epoch","metric":"epoch_fiction_livebench_at_8k","value":0.972,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"epoch","metric":"epoch_fiction_livebench_at_32k","value":0.806,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"epoch","metric":"epoch_fiction_livebench_at_60k","value":0.778,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"epoch","metric":"epoch_fiction_livebench_at_120k","value":0.688,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"epoch","metric":"epoch_fiction_livebench","value":0.556,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"epoch","metric":"epoch_fiction_livebench_at_0","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"epoch","metric":"epoch_fiction_livebench_at_400","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"epoch","metric":"epoch_fiction_livebench_at_1k","value":0.722,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"epoch","metric":"epoch_fiction_livebench_at_2k","value":0.639,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"epoch","metric":"epoch_fiction_livebench_at_4k","value":0.611,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"epoch","metric":"epoch_fiction_livebench_at_8k","value":0.583,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"epoch","metric":"epoch_fiction_livebench_at_32k","value":0.528,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"epoch","metric":"epoch_fiction_livebench_at_60k","value":0.556,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"epoch","metric":"epoch_fiction_livebench_at_120k","value":0.625,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"epoch","metric":"epoch_fiction_livebench_at_192k","value":0.469,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"epoch","metric":"epoch_fiction_livebench","value":0.833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"epoch","metric":"epoch_fiction_livebench_at_0","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"epoch","metric":"epoch_fiction_livebench_at_400","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"epoch","metric":"epoch_fiction_livebench_at_1k","value":0.972,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"epoch","metric":"epoch_fiction_livebench_at_2k","value":0.972,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"epoch","metric":"epoch_fiction_livebench_at_4k","value":0.917,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"epoch","metric":"epoch_fiction_livebench_at_8k","value":0.944,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"epoch","metric":"epoch_fiction_livebench_at_32k","value":0.833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"epoch","metric":"epoch_fiction_livebench_at_60k","value":0.714,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"google/gemini-2.5-pro-preview","source":"epoch","metric":"epoch_fiction_livebench","value":0.917,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"google/gemini-2.5-pro-preview","source":"epoch","metric":"epoch_fiction_livebench_at_0","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"google/gemini-2.5-pro-preview","source":"epoch","metric":"epoch_fiction_livebench_at_400","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"google/gemini-2.5-pro-preview","source":"epoch","metric":"epoch_fiction_livebench_at_1k","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"google/gemini-2.5-pro-preview","source":"epoch","metric":"epoch_fiction_livebench_at_2k","value":0.972,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"google/gemini-2.5-pro-preview","source":"epoch","metric":"epoch_fiction_livebench_at_4k","value":0.944,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"google/gemini-2.5-pro-preview","source":"epoch","metric":"epoch_fiction_livebench_at_8k","value":0.806,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"google/gemini-2.5-pro-preview","source":"epoch","metric":"epoch_fiction_livebench_at_32k","value":0.917,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"google/gemini-2.5-pro-preview","source":"epoch","metric":"epoch_fiction_livebench_at_60k","value":0.833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"google/gemini-2.5-pro-preview","source":"epoch","metric":"epoch_fiction_livebench_at_120k","value":0.875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"google/gemini-2.5-pro-preview","source":"epoch","metric":"epoch_fiction_livebench_at_192k","value":0.906,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-4.1","source":"epoch","metric":"epoch_fiction_livebench","value":0.639,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-4.1","source":"epoch","metric":"epoch_fiction_livebench_at_0","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-4.1","source":"epoch","metric":"epoch_fiction_livebench_at_400","value":0.917,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-4.1","source":"epoch","metric":"epoch_fiction_livebench_at_1k","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-4.1","source":"epoch","metric":"epoch_fiction_livebench_at_2k","value":0.694,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-4.1","source":"epoch","metric":"epoch_fiction_livebench_at_4k","value":0.639,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-4.1","source":"epoch","metric":"epoch_fiction_livebench_at_8k","value":0.556,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-4.1","source":"epoch","metric":"epoch_fiction_livebench_at_32k","value":0.583,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-4.1","source":"epoch","metric":"epoch_fiction_livebench_at_60k","value":0.528,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-4.1","source":"epoch","metric":"epoch_fiction_livebench_at_120k","value":0.625,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-4.1","source":"epoch","metric":"epoch_fiction_livebench_at_192k","value":0.563,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_fiction_livebench","value":0.972,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_fiction_livebench_at_0","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_fiction_livebench_at_400","value":0.972,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_fiction_livebench_at_1k","value":0.944,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_fiction_livebench_at_2k","value":0.972,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_fiction_livebench_at_4k","value":0.972,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_fiction_livebench_at_8k","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_fiction_livebench_at_32k","value":0.972,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_fiction_livebench_at_60k","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_fiction_livebench_at_120k","value":0.969,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_fiction_livebench_at_192k","value":0.875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_fiction_livebench","value":0.694,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_fiction_livebench_at_0","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_fiction_livebench_at_400","value":0.972,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_fiction_livebench_at_1k","value":0.889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_fiction_livebench_at_2k","value":0.806,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_fiction_livebench_at_4k","value":0.778,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_fiction_livebench_at_8k","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_fiction_livebench_at_32k","value":0.639,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_fiction_livebench_at_60k","value":0.611,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_fiction_livebench_at_120k","value":0.625,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_fiction_livebench_at_192k","value":0.594,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"moonshotai/kimi-k2.5","source":"epoch","metric":"epoch_fiction_livebench","value":0.861,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"moonshotai/kimi-k2.5","source":"epoch","metric":"epoch_fiction_livebench_at_0","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"moonshotai/kimi-k2.5","source":"epoch","metric":"epoch_fiction_livebench_at_400","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"moonshotai/kimi-k2.5","source":"epoch","metric":"epoch_fiction_livebench_at_1k","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"moonshotai/kimi-k2.5","source":"epoch","metric":"epoch_fiction_livebench_at_2k","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"moonshotai/kimi-k2.5","source":"epoch","metric":"epoch_fiction_livebench_at_4k","value":0.944,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"moonshotai/kimi-k2.5","source":"epoch","metric":"epoch_fiction_livebench_at_8k","value":0.889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"moonshotai/kimi-k2.5","source":"epoch","metric":"epoch_fiction_livebench_at_32k","value":0.889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"moonshotai/kimi-k2.5","source":"epoch","metric":"epoch_fiction_livebench_at_60k","value":0.889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"moonshotai/kimi-k2.5","source":"epoch","metric":"epoch_fiction_livebench_at_120k","value":0.781,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"moonshotai/kimi-k2.5","source":"epoch","metric":"epoch_fiction_livebench_at_192k","value":0.875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o1","source":"epoch","metric":"epoch_fiction_livebench","value":0.833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o1","source":"epoch","metric":"epoch_fiction_livebench_at_0","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o1","source":"epoch","metric":"epoch_fiction_livebench_at_400","value":0.972,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o1","source":"epoch","metric":"epoch_fiction_livebench_at_1k","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o1","source":"epoch","metric":"epoch_fiction_livebench_at_2k","value":0.944,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o1","source":"epoch","metric":"epoch_fiction_livebench_at_4k","value":0.944,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o1","source":"epoch","metric":"epoch_fiction_livebench_at_8k","value":0.861,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o1","source":"epoch","metric":"epoch_fiction_livebench_at_32k","value":0.833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o1","source":"epoch","metric":"epoch_fiction_livebench_at_60k","value":0.722,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o1","source":"epoch","metric":"epoch_fiction_livebench_at_120k","value":0.531,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_fiction_livebench","value":0.889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_fiction_livebench_at_0","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_fiction_livebench_at_400","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_fiction_livebench_at_1k","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_fiction_livebench_at_2k","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_fiction_livebench_at_4k","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_fiction_livebench_at_8k","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_fiction_livebench_at_32k","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_fiction_livebench_at_60k","value":0.833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_fiction_livebench_at_120k","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_fiction_livebench_at_192k","value":0.581,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o3-mini","source":"epoch","metric":"epoch_fiction_livebench","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o3-mini","source":"epoch","metric":"epoch_fiction_livebench_at_0","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o3-mini","source":"epoch","metric":"epoch_fiction_livebench_at_400","value":0.639,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o3-mini","source":"epoch","metric":"epoch_fiction_livebench_at_1k","value":0.583,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o3-mini","source":"epoch","metric":"epoch_fiction_livebench_at_2k","value":0.472,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o3-mini","source":"epoch","metric":"epoch_fiction_livebench_at_4k","value":0.472,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o3-mini","source":"epoch","metric":"epoch_fiction_livebench_at_8k","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o3-mini","source":"epoch","metric":"epoch_fiction_livebench_at_32k","value":0.556,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o3-mini","source":"epoch","metric":"epoch_fiction_livebench_at_60k","value":0.444,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o3-mini","source":"epoch","metric":"epoch_fiction_livebench_at_120k","value":0.438,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o3-pro","source":"epoch","metric":"epoch_fiction_livebench","value":0.972,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o3-pro","source":"epoch","metric":"epoch_fiction_livebench_at_0","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o3-pro","source":"epoch","metric":"epoch_fiction_livebench_at_400","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o3-pro","source":"epoch","metric":"epoch_fiction_livebench_at_1k","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o3-pro","source":"epoch","metric":"epoch_fiction_livebench_at_2k","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o3-pro","source":"epoch","metric":"epoch_fiction_livebench_at_4k","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o3-pro","source":"epoch","metric":"epoch_fiction_livebench_at_8k","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o3-pro","source":"epoch","metric":"epoch_fiction_livebench_at_32k","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o3-pro","source":"epoch","metric":"epoch_fiction_livebench_at_60k","value":0.944,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o3-pro","source":"epoch","metric":"epoch_fiction_livebench_at_120k","value":0.889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o3-pro","source":"epoch","metric":"epoch_fiction_livebench_at_192k","value":0.656,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_fiction_livebench","value":0.778,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_fiction_livebench_at_0","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_fiction_livebench_at_400","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_fiction_livebench_at_1k","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_fiction_livebench_at_2k","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_fiction_livebench_at_4k","value":0.778,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_fiction_livebench_at_8k","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_fiction_livebench_at_32k","value":0.556,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_fiction_livebench_at_60k","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_fiction_livebench_at_120k","value":0.625,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_fiction_livebench_at_192k","value":0.438,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"epoch","metric":"epoch_fiction_livebench","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"epoch","metric":"epoch_fiction_livebench_at_0","value":0.875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"epoch","metric":"epoch_fiction_livebench_at_400","value":0.611,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"epoch","metric":"epoch_fiction_livebench_at_1k","value":0.694,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"epoch","metric":"epoch_fiction_livebench_at_2k","value":0.528,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"epoch","metric":"epoch_fiction_livebench_at_4k","value":0.528,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"epoch","metric":"epoch_fiction_livebench_at_8k","value":0.528,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"epoch","metric":"epoch_fiction_livebench_at_32k","value":0.556,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"epoch","metric":"epoch_fiction_livebench_at_60k","value":0.556,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"google/gemma-3-27b-it","source":"epoch","metric":"epoch_fiction_livebench","value":0.333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"google/gemma-3-27b-it","source":"epoch","metric":"epoch_fiction_livebench_at_0","value":0.875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"google/gemma-3-27b-it","source":"epoch","metric":"epoch_fiction_livebench_at_400","value":0.444,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"google/gemma-3-27b-it","source":"epoch","metric":"epoch_fiction_livebench_at_1k","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"google/gemma-3-27b-it","source":"epoch","metric":"epoch_fiction_livebench_at_2k","value":0.417,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"google/gemma-3-27b-it","source":"epoch","metric":"epoch_fiction_livebench_at_4k","value":0.333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"google/gemma-3-27b-it","source":"epoch","metric":"epoch_fiction_livebench_at_8k","value":0.389,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"google/gemma-3-27b-it","source":"epoch","metric":"epoch_fiction_livebench_at_32k","value":0.25,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"google/gemma-3-27b-it","source":"epoch","metric":"epoch_fiction_livebench_at_60k","value":0.306,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"moonshotai/kimi-k2-0905","source":"epoch","metric":"epoch_fiction_livebench","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"moonshotai/kimi-k2-0905","source":"epoch","metric":"epoch_fiction_livebench_at_0","value":0.875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"moonshotai/kimi-k2-0905","source":"epoch","metric":"epoch_fiction_livebench_at_400","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"moonshotai/kimi-k2-0905","source":"epoch","metric":"epoch_fiction_livebench_at_1k","value":0.722,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"moonshotai/kimi-k2-0905","source":"epoch","metric":"epoch_fiction_livebench_at_2k","value":0.722,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"moonshotai/kimi-k2-0905","source":"epoch","metric":"epoch_fiction_livebench_at_4k","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"moonshotai/kimi-k2-0905","source":"epoch","metric":"epoch_fiction_livebench_at_8k","value":0.583,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"moonshotai/kimi-k2-0905","source":"epoch","metric":"epoch_fiction_livebench_at_32k","value":0.639,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"moonshotai/kimi-k2-0905","source":"epoch","metric":"epoch_fiction_livebench_at_60k","value":0.556,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"moonshotai/kimi-k2-0905","source":"epoch","metric":"epoch_fiction_livebench_at_120k","value":0.406,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"moonshotai/kimi-k2-0905","source":"epoch","metric":"epoch_fiction_livebench_at_192k","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"moonshotai/kimi-k2","source":"epoch","metric":"epoch_fiction_livebench","value":0.611,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"moonshotai/kimi-k2","source":"epoch","metric":"epoch_fiction_livebench_at_0","value":0.875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"moonshotai/kimi-k2","source":"epoch","metric":"epoch_fiction_livebench_at_400","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"moonshotai/kimi-k2","source":"epoch","metric":"epoch_fiction_livebench_at_1k","value":0.694,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"moonshotai/kimi-k2","source":"epoch","metric":"epoch_fiction_livebench_at_2k","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"moonshotai/kimi-k2","source":"epoch","metric":"epoch_fiction_livebench_at_4k","value":0.583,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"moonshotai/kimi-k2","source":"epoch","metric":"epoch_fiction_livebench_at_8k","value":0.556,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"moonshotai/kimi-k2","source":"epoch","metric":"epoch_fiction_livebench_at_32k","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"moonshotai/kimi-k2","source":"epoch","metric":"epoch_fiction_livebench_at_60k","value":0.444,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-30b-a3b","source":"epoch","metric":"epoch_fiction_livebench","value":0.406,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-30b-a3b","source":"epoch","metric":"epoch_fiction_livebench_at_0","value":0.857,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-30b-a3b","source":"epoch","metric":"epoch_fiction_livebench_at_400","value":0.581,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-30b-a3b","source":"epoch","metric":"epoch_fiction_livebench_at_1k","value":0.548,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-30b-a3b","source":"epoch","metric":"epoch_fiction_livebench_at_2k","value":0.515,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-30b-a3b","source":"epoch","metric":"epoch_fiction_livebench_at_4k","value":0.533,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-30b-a3b","source":"epoch","metric":"epoch_fiction_livebench_at_8k","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-14b","source":"epoch","metric":"epoch_fiction_livebench","value":0.625,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-14b","source":"epoch","metric":"epoch_fiction_livebench_at_0","value":0.833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-14b","source":"epoch","metric":"epoch_fiction_livebench_at_400","value":0.645,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-14b","source":"epoch","metric":"epoch_fiction_livebench_at_1k","value":0.618,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-14b","source":"epoch","metric":"epoch_fiction_livebench_at_2k","value":0.594,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-14b","source":"epoch","metric":"epoch_fiction_livebench_at_4k","value":0.647,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-14b","source":"epoch","metric":"epoch_fiction_livebench_at_8k","value":0.516,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-32b","source":"epoch","metric":"epoch_fiction_livebench","value":0.742,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-32b","source":"epoch","metric":"epoch_fiction_livebench_at_0","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-32b","source":"epoch","metric":"epoch_fiction_livebench_at_400","value":0.909,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-32b","source":"epoch","metric":"epoch_fiction_livebench_at_1k","value":0.938,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-32b","source":"epoch","metric":"epoch_fiction_livebench_at_2k","value":0.767,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-32b","source":"epoch","metric":"epoch_fiction_livebench_at_4k","value":0.867,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"qwen/qwen3-32b","source":"epoch","metric":"epoch_fiction_livebench_at_8k","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-4.1-mini","source":"epoch","metric":"epoch_fiction_livebench","value":0.444,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-4.1-mini","source":"epoch","metric":"epoch_fiction_livebench_at_0","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-4.1-mini","source":"epoch","metric":"epoch_fiction_livebench_at_400","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-4.1-mini","source":"epoch","metric":"epoch_fiction_livebench_at_1k","value":0.556,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-4.1-mini","source":"epoch","metric":"epoch_fiction_livebench_at_2k","value":0.417,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-4.1-mini","source":"epoch","metric":"epoch_fiction_livebench_at_4k","value":0.444,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-4.1-mini","source":"epoch","metric":"epoch_fiction_livebench_at_8k","value":0.417,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-4.1-mini","source":"epoch","metric":"epoch_fiction_livebench_at_32k","value":0.389,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-4.1-mini","source":"epoch","metric":"epoch_fiction_livebench_at_60k","value":0.389,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-4.1-mini","source":"epoch","metric":"epoch_fiction_livebench_at_120k","value":0.469,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-5-nano","source":"epoch","metric":"epoch_fiction_livebench","value":0.444,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-5-nano","source":"epoch","metric":"epoch_fiction_livebench_at_0","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-5-nano","source":"epoch","metric":"epoch_fiction_livebench_at_400","value":0.583,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-5-nano","source":"epoch","metric":"epoch_fiction_livebench_at_1k","value":0.639,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-5-nano","source":"epoch","metric":"epoch_fiction_livebench_at_2k","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-5-nano","source":"epoch","metric":"epoch_fiction_livebench_at_4k","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-5-nano","source":"epoch","metric":"epoch_fiction_livebench_at_8k","value":0.528,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-5-nano","source":"epoch","metric":"epoch_fiction_livebench_at_32k","value":0.472,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-5-nano","source":"epoch","metric":"epoch_fiction_livebench_at_60k","value":0.361,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-5-nano","source":"epoch","metric":"epoch_fiction_livebench_at_120k","value":0.219,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-5-nano","source":"epoch","metric":"epoch_fiction_livebench_at_192k","value":0.344,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"epoch","metric":"epoch_fiction_livebench","value":0.333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"epoch","metric":"epoch_fiction_livebench_at_0","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"epoch","metric":"epoch_fiction_livebench_at_400","value":0.667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"epoch","metric":"epoch_fiction_livebench_at_1k","value":0.694,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"epoch","metric":"epoch_fiction_livebench_at_2k","value":0.556,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"epoch","metric":"epoch_fiction_livebench_at_4k","value":0.417,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"epoch","metric":"epoch_fiction_livebench_at_8k","value":0.361,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"epoch","metric":"epoch_fiction_livebench_at_32k","value":0.333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"epoch","metric":"epoch_fiction_livebench_at_60k","value":0.333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"meta-llama/llama-4-scout","source":"epoch","metric":"epoch_fiction_livebench","value":0.36,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"meta-llama/llama-4-scout","source":"epoch","metric":"epoch_fiction_livebench_at_0","value":0.625,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"meta-llama/llama-4-scout","source":"epoch","metric":"epoch_fiction_livebench_at_400","value":0.52,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"meta-llama/llama-4-scout","source":"epoch","metric":"epoch_fiction_livebench_at_1k","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"meta-llama/llama-4-scout","source":"epoch","metric":"epoch_fiction_livebench_at_2k","value":0.36,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"meta-llama/llama-4-scout","source":"epoch","metric":"epoch_fiction_livebench_at_4k","value":0.32,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"meta-llama/llama-4-scout","source":"epoch","metric":"epoch_fiction_livebench_at_8k","value":0.4,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"meta-llama/llama-4-scout","source":"epoch","metric":"epoch_fiction_livebench_at_32k","value":0.16,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"meta-llama/llama-4-scout","source":"epoch","metric":"epoch_fiction_livebench_at_60k","value":0.24,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"meta-llama/llama-4-scout","source":"epoch","metric":"epoch_fiction_livebench_at_120k","value":0.273,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-4.1-nano","source":"epoch","metric":"epoch_fiction_livebench","value":0.25,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-4.1-nano","source":"epoch","metric":"epoch_fiction_livebench_at_0","value":0.625,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-4.1-nano","source":"epoch","metric":"epoch_fiction_livebench_at_400","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-4.1-nano","source":"epoch","metric":"epoch_fiction_livebench_at_1k","value":0.417,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-4.1-nano","source":"epoch","metric":"epoch_fiction_livebench_at_2k","value":0.361,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-4.1-nano","source":"epoch","metric":"epoch_fiction_livebench_at_4k","value":0.333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-4.1-nano","source":"epoch","metric":"epoch_fiction_livebench_at_8k","value":0.389,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-4.1-nano","source":"epoch","metric":"epoch_fiction_livebench_at_32k","value":0.333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-4.1-nano","source":"epoch","metric":"epoch_fiction_livebench_at_60k","value":0.361,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/gpt-4.1-nano","source":"epoch","metric":"epoch_fiction_livebench_at_120k","value":0.188,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://fiction.live/stories/Fiction-liveBench-Mar-14-2025/oQdzQvKHw8JyXbN87/home"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_lech_mazur_writing","value":0.8390000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://github.com/lechmazur/Writing"},{"modelId":"openai/gpt-4o-2024-11-20","source":"epoch","metric":"epoch_lech_mazur_writing","value":0.8180000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://github.com/lechmazur/Writing"},{"modelId":"google/gemma-3-27b-it","source":"epoch","metric":"epoch_lech_mazur_writing","value":0.799,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://github.com/lechmazur/Writing"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"epoch","metric":"epoch_lech_mazur_writing","value":0.77,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://github.com/lechmazur/Writing"},{"modelId":"qwen/qwen3-30b-a3b","source":"epoch","metric":"epoch_lech_mazur_writing","value":0.7530000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://github.com/lechmazur/Writing"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_lech_mazur_writing","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://github.com/lechmazur/Writing"},{"modelId":"openai/o1","source":"epoch","metric":"epoch_lech_mazur_writing","value":0.702,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://github.com/lechmazur/Writing"},{"modelId":"mistralai/mistral-large-2407","source":"epoch","metric":"epoch_lech_mazur_writing","value":0.6900000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://github.com/lechmazur/Writing"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"epoch","metric":"epoch_lech_mazur_writing","value":0.672,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://github.com/lechmazur/Writing"},{"modelId":"microsoft/phi-4","source":"epoch","metric":"epoch_lech_mazur_writing","value":0.626,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://github.com/lechmazur/Writing"},{"modelId":"meta-llama/llama-4-maverick","source":"epoch","metric":"epoch_lech_mazur_writing","value":0.6200000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://github.com/lechmazur/Writing"},{"modelId":"openai/o3-mini","source":"epoch","metric":"epoch_lech_mazur_writing","value":0.617,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://github.com/lechmazur/Writing"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_lech_mazur_writing","value":0.86,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://github.com/lechmazur/Writing"},{"modelId":"moonshotai/kimi-k2","source":"epoch","metric":"epoch_lech_mazur_writing","value":0.8560000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://github.com/lechmazur/Writing"},{"modelId":"openai/o3-pro","source":"epoch","metric":"epoch_lech_mazur_writing","value":0.844,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://github.com/lechmazur/Writing"},{"modelId":"google/gemini-2.5-pro","source":"epoch","metric":"epoch_lech_mazur_writing","value":0.8380000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://github.com/lechmazur/Writing"},{"modelId":"anthropic/claude-opus-4.1","source":"epoch","metric":"epoch_lech_mazur_writing","value":0.8470000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://github.com/lechmazur/Writing"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"epoch","metric":"epoch_lech_mazur_writing","value":0.8240000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://github.com/lechmazur/Writing"},{"modelId":"z-ai/glm-4.5","source":"epoch","metric":"epoch_lech_mazur_writing","value":0.734,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://github.com/lechmazur/Writing"},{"modelId":"openai/gpt-oss-120b","source":"epoch","metric":"epoch_lech_mazur_writing","value":0.771,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://github.com/lechmazur/Writing"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_lech_mazur_writing","value":0.8310000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://github.com/lechmazur/Writing"},{"modelId":"deepseek/deepseek-r1-0528","source":"epoch","metric":"epoch_lech_mazur_writing","value":0.819,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://github.com/lechmazur/Writing"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_cl_bench","value":0.279,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.1","source":"epoch","metric":"epoch_cl_bench","value":0.237,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.20","source":"epoch","metric":"epoch_cl_bench","value":0.222,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_cl_bench","value":0.211,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_cl_bench","value":0.20800000000000002,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.6","source":"epoch","metric":"epoch_cl_bench","value":0.207,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.6-plus","source":"epoch","metric":"epoch_cl_bench","value":0.203,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"epoch","metric":"epoch_cl_bench","value":0.198,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k2.5","source":"epoch","metric":"epoch_cl_bench","value":0.193,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5","source":"epoch","metric":"epoch_cl_bench","value":0.187,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.2","source":"epoch","metric":"epoch_cl_bench","value":0.182,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_cl_bench","value":0.17800000000000002,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k2-thinking","source":"epoch","metric":"epoch_cl_bench","value":0.176,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-4.7","source":"epoch","metric":"epoch_cl_bench","value":0.159,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"epoch","metric":"epoch_cl_bench","value":0.132,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v3.2","source":"epoch","metric":"epoch_cl_bench","value":0.12400000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k2","source":"epoch","metric":"epoch_cl_bench","value":0.119,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"minimax/minimax-m2.5","source":"epoch","metric":"epoch_cl_bench","value":0.114,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_surface_evolver","value":0.9500000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_surface_evolver_cost_usd","value":19.43522,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_surface_evolver_pass_rate","value":0.875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_surface_evolver_tokens","value":933342,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_surface_evolver","value":0.93125,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_surface_evolver_cost_usd","value":9.407759,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_surface_evolver_pass_rate","value":0.875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_surface_evolver_tokens","value":1415604,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_surface_evolver","value":0.88125,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_surface_evolver_cost_usd","value":13.825813,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_surface_evolver_pass_rate","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_surface_evolver_tokens","value":2033603,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_surface_evolver","value":0.9500000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_surface_evolver_cost_usd","value":12.142178,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_surface_evolver_pass_rate","value":0.875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_surface_evolver_tokens","value":3710719,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_surface_evolver","value":0.875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_surface_evolver_cost_usd","value":21.961645,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_surface_evolver_pass_rate","value":0.6875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_surface_evolver_tokens","value":2699281,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_surface_evolver","value":0.8375,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_surface_evolver_cost_usd","value":7.589903,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_surface_evolver_pass_rate","value":0.6875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_surface_evolver_tokens","value":2127318,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"x-ai/grok-4.5","source":"epoch","metric":"epoch_surface_evolver","value":0.74375,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"x-ai/grok-4.5","source":"epoch","metric":"epoch_surface_evolver_cost_usd","value":4.610306,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"x-ai/grok-4.5","source":"epoch","metric":"epoch_surface_evolver_pass_rate","value":0.5,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"x-ai/grok-4.5","source":"epoch","metric":"epoch_surface_evolver_tokens","value":3055609,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"moonshotai/kimi-k2.7-code","source":"epoch","metric":"epoch_surface_evolver","value":0.4875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"moonshotai/kimi-k2.7-code","source":"epoch","metric":"epoch_surface_evolver_cost_usd","value":4.032123,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"moonshotai/kimi-k2.7-code","source":"epoch","metric":"epoch_surface_evolver_pass_rate","value":0.375,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"moonshotai/kimi-k2.7-code","source":"epoch","metric":"epoch_surface_evolver_tokens","value":5324288,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_surface_evolver","value":0.55625,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_surface_evolver_cost_usd","value":4.646197,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_surface_evolver_pass_rate","value":0.3125,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_surface_evolver_tokens","value":2543170,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"deepseek/deepseek-v4-pro","source":"epoch","metric":"epoch_surface_evolver","value":0.4,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"deepseek/deepseek-v4-pro","source":"epoch","metric":"epoch_surface_evolver_cost_usd","value":3.857009,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"deepseek/deepseek-v4-pro","source":"epoch","metric":"epoch_surface_evolver_pass_rate","value":0.25,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"deepseek/deepseek-v4-pro","source":"epoch","metric":"epoch_surface_evolver_tokens","value":4495515,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_surface_evolver","value":0.61875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_surface_evolver_cost_usd","value":1.007941,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_surface_evolver_pass_rate","value":0.1875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_surface_evolver_tokens","value":1243407,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"minimax/minimax-m3","source":"epoch","metric":"epoch_surface_evolver","value":0.5499999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"minimax/minimax-m3","source":"epoch","metric":"epoch_surface_evolver_cost_usd","value":2.078064,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"minimax/minimax-m3","source":"epoch","metric":"epoch_surface_evolver_pass_rate","value":0.1875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"minimax/minimax-m3","source":"epoch","metric":"epoch_surface_evolver_tokens","value":5547086,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"qwen/qwen3.6-35b-a3b","source":"epoch","metric":"epoch_surface_evolver","value":0.44375000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"qwen/qwen3.6-35b-a3b","source":"epoch","metric":"epoch_surface_evolver_cost_usd","value":2.192583,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"qwen/qwen3.6-35b-a3b","source":"epoch","metric":"epoch_surface_evolver_pass_rate","value":0.125,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"qwen/qwen3.6-35b-a3b","source":"epoch","metric":"epoch_surface_evolver_tokens","value":4037755,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"google/gemma-4-31b-it","source":"epoch","metric":"epoch_surface_evolver","value":0.30624999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"google/gemma-4-31b-it","source":"epoch","metric":"epoch_surface_evolver_cost_usd","value":0.215576,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"google/gemma-4-31b-it","source":"epoch","metric":"epoch_surface_evolver_pass_rate","value":0.0625,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"google/gemma-4-31b-it","source":"epoch","metric":"epoch_surface_evolver_tokens","value":1419535,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"openai/gpt-oss-120b","source":"epoch","metric":"epoch_surface_evolver","value":0.25,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"openai/gpt-oss-120b","source":"epoch","metric":"epoch_surface_evolver_cost_usd","value":0.089232,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"openai/gpt-oss-120b","source":"epoch","metric":"epoch_surface_evolver_pass_rate","value":0.0625,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"openai/gpt-oss-120b","source":"epoch","metric":"epoch_surface_evolver_tokens","value":1475754,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"google/gemini-3.5-flash","source":"epoch","metric":"epoch_surface_evolver","value":0.58125,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"google/gemini-3.5-flash","source":"epoch","metric":"epoch_surface_evolver_cost_usd","value":6.638204,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"google/gemini-3.5-flash","source":"epoch","metric":"epoch_surface_evolver_pass_rate","value":0.375,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"google/gemini-3.5-flash","source":"epoch","metric":"epoch_surface_evolver_tokens","value":3108560,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"anthropic/claude-sonnet-5","source":"epoch","metric":"epoch_surface_evolver","value":0.6,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"anthropic/claude-sonnet-5","source":"epoch","metric":"epoch_surface_evolver_cost_usd","value":11.938944,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"anthropic/claude-sonnet-5","source":"epoch","metric":"epoch_surface_evolver_pass_rate","value":0.1875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"anthropic/claude-sonnet-5","source":"epoch","metric":"epoch_surface_evolver_tokens","value":3783644,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"mistralai/mistral-medium-3-5","source":"epoch","metric":"epoch_surface_evolver","value":0.26875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"mistralai/mistral-medium-3-5","source":"epoch","metric":"epoch_surface_evolver_cost_usd","value":6.348204,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"mistralai/mistral-medium-3-5","source":"epoch","metric":"epoch_surface_evolver_pass_rate","value":0.0625,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"mistralai/mistral-medium-3-5","source":"epoch","metric":"epoch_surface_evolver_tokens","value":2760172,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"arcee-ai/trinity-large-thinking","source":"epoch","metric":"epoch_surface_evolver","value":0.15625,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"arcee-ai/trinity-large-thinking","source":"epoch","metric":"epoch_surface_evolver_cost_usd","value":1.247193,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"arcee-ai/trinity-large-thinking","source":"epoch","metric":"epoch_surface_evolver_pass_rate","value":0.0625,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"arcee-ai/trinity-large-thinking","source":"epoch","metric":"epoch_surface_evolver_tokens","value":2601726,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"meta/muse-spark-1.1","source":"epoch","metric":"epoch_surface_evolver","value":0.525,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"meta/muse-spark-1.1","source":"epoch","metric":"epoch_surface_evolver_cost_usd","value":2.498339,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"meta/muse-spark-1.1","source":"epoch","metric":"epoch_surface_evolver_pass_rate","value":0.375,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"meta/muse-spark-1.1","source":"epoch","metric":"epoch_surface_evolver_tokens","value":3800825,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"qwen/qwen3.8-27b","source":"epoch","metric":"epoch_surface_evolver","value":0.45,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"qwen/qwen3.8-27b","source":"epoch","metric":"epoch_surface_evolver_cost_usd","value":9.048761,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"qwen/qwen3.8-27b","source":"epoch","metric":"epoch_surface_evolver_pass_rate","value":0.1875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"qwen/qwen3.8-27b","source":"epoch","metric":"epoch_surface_evolver_tokens","value":4703787,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"z-ai/glm-5.3-flash","source":"epoch","metric":"epoch_surface_evolver","value":0.525,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"z-ai/glm-5.3-flash","source":"epoch","metric":"epoch_surface_evolver_cost_usd","value":0.308535,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"z-ai/glm-5.3-flash","source":"epoch","metric":"epoch_surface_evolver_pass_rate","value":0.1875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"z-ai/glm-5.3-flash","source":"epoch","metric":"epoch_surface_evolver_tokens","value":2619902,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_surface_evolver","value":0.76875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_surface_evolver_cost_usd","value":2.598115,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_surface_evolver_pass_rate","value":0.5625,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_surface_evolver_tokens","value":3212425,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"epoch","metric":"epoch_surface_evolver","value":0.4625,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"epoch","metric":"epoch_surface_evolver_cost_usd","value":2.127708,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"epoch","metric":"epoch_surface_evolver_pass_rate","value":0.3125,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"epoch","metric":"epoch_surface_evolver_tokens","value":3347576,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"mistralai/mistral-large-4-0","source":"epoch","metric":"epoch_surface_evolver","value":0.28125,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"mistralai/mistral-large-4-0","source":"epoch","metric":"epoch_surface_evolver_cost_usd","value":6.017185,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"mistralai/mistral-large-4-0","source":"epoch","metric":"epoch_surface_evolver_pass_rate","value":0.1875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"mistralai/mistral-large-4-0","source":"epoch","metric":"epoch_surface_evolver_tokens","value":5653545,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://yhenon.github.io/surface-evolver-llm-eval/"},{"modelId":"mistralai/mistral-large-4-0","source":"epoch","metric":"epoch_furniture_assembly","value":0.20833333333333334,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-4-argon","source":"epoch","metric":"epoch_furniture_assembly","value":0.725,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"epoch","metric":"epoch_furniture_assembly","value":0.3416666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-haiku-5.5","source":"epoch","metric":"epoch_furniture_assembly","value":0.475,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6.1-sol","source":"epoch","metric":"epoch_furniture_assembly","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-5.5","source":"epoch","metric":"epoch_furniture_assembly","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-luna","source":"epoch","metric":"epoch_furniture_assembly","value":0.44166666666666665,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.5","source":"epoch","metric":"epoch_furniture_assembly","value":0.225,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_furniture_assembly","value":0.4,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.7","source":"epoch","metric":"epoch_furniture_assembly","value":0.20833333333333334,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-sol","source":"epoch","metric":"epoch_furniture_assembly","value":0.5833333333333334,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-5.5","source":"epoch","metric":"epoch_furniture_assembly","value":0.8333333333333334,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_furniture_assembly","value":0.3416666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k2.6","source":"epoch","metric":"epoch_furniture_assembly","value":0.21666666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.8-max-0902","source":"epoch","metric":"epoch_furniture_assembly","value":0.2,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.7-flash","source":"epoch","metric":"epoch_furniture_assembly","value":0.26666666666666666,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.6-flash","source":"epoch","metric":"epoch_furniture_assembly","value":0.23333333333333334,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_furniture_assembly","value":0.31666666666666665,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-fable-5.1","source":"epoch","metric":"epoch_furniture_assembly","value":0.7,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_furniture_assembly","value":0.26666666666666666,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_furniture_assembly","value":0.35833333333333334,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_furniture_assembly","value":0.6083333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_furniture_assembly","value":0.425,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.7","source":"epoch","metric":"epoch_furniture_assembly","value":0.3333333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.6","source":"epoch","metric":"epoch_furniture_assembly","value":0.2833333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_furniture_assembly","value":0.2833333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_furniture_assembly","value":0.425,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_furniture_assembly","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_furniture_assembly","value":0.5666666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_furniture_assembly","value":0.5416666666666666,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_furniture_assembly","value":0.44166666666666665,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.2","source":"epoch","metric":"epoch_furniture_assembly","value":0.38333333333333336,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_furniture_assembly","value":0.375,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_exploitbench","value":0.474,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.7","source":"epoch","metric":"epoch_exploitbench","value":0.265,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_exploitbench","value":0.261,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-4.6","source":"epoch","metric":"epoch_exploitbench","value":0.23600000000000002,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k2.6","source":"epoch","metric":"epoch_exploitbench","value":0.184,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-5.1","source":"epoch","metric":"epoch_exploitbench","value":0.18100000000000002,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-haiku-4.5","source":"epoch","metric":"epoch_exploitbench","value":0.13699999999999998,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"minimax/minimax-m2.7","source":"epoch","metric":"epoch_exploitbench","value":0.133,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.6","source":"epoch","metric":"epoch_cybench","value":0.93,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www-cdn.anthropic.com/0dd865075ad3132672ee0ab40b05a53f14cf5288.pdf"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_cybench","value":0.82,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://assets.anthropic.com/m/64823ba7485345a7/Claude-Opus-4-5-System-Card.pdf"},{"modelId":"anthropic/claude-sonnet-4.5","source":"epoch","metric":"epoch_cybench","value":0.6,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://assets.anthropic.com/m/64823ba7485345a7/Claude-Opus-4-5-System-Card.pdf"},{"modelId":"anthropic/claude-opus-4.1","source":"epoch","metric":"epoch_cybench","value":0.42,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cybench.github.io/"},{"modelId":"openai/o3-mini","source":"epoch","metric":"epoch_cybench","value":0.225,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cybench.github.io/"},{"modelId":"openai/gpt-4o-2024-11-20","source":"epoch","metric":"epoch_cybench","value":0.125,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cybench.github.io/"},{"modelId":"openai/gpt-4o-2024-11-20","source":"epoch","metric":"epoch_the_agent_company","value":0.086,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://github.com/TheAgentCompany/experiments/tree/main/evaluation/1.0.0/20241217_OpenHands-0.14.2-gpt-4o-2024-08-06"},{"modelId":"openai/gpt-4o-2024-11-20","source":"epoch","metric":"epoch_the_agent_company_cost_usd","value":1.29,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://github.com/TheAgentCompany/experiments/tree/main/evaluation/1.0.0/20241217_OpenHands-0.14.2-gpt-4o-2024-08-06"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"epoch","metric":"epoch_the_agent_company","value":0.069,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://github.com/TheAgentCompany/experiments/tree/main/evaluation/1.0.0/20241217_OpenHands-0.14.2-llama-3.3-70b"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"epoch","metric":"epoch_the_agent_company_cost_usd","value":0.93,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://github.com/TheAgentCompany/experiments/tree/main/evaluation/1.0.0/20241217_OpenHands-0.14.2-llama-3.3-70b"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"epoch","metric":"epoch_the_agent_company","value":0.057,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://github.com/TheAgentCompany/experiments/tree/main/evaluation/1.0.0/20241217_OpenHands-0.14.2-qwen2.5-72b"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"epoch","metric":"epoch_the_agent_company_cost_usd","value":1.53,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://github.com/TheAgentCompany/experiments/tree/main/evaluation/1.0.0/20241217_OpenHands-0.14.2-qwen2.5-72b"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"epoch","metric":"epoch_the_agent_company","value":0.429,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://the-agent-company.com/#/leaderboard"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"epoch","metric":"epoch_the_agent_company_cost_usd","value":0.4,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://the-agent-company.com/#/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.6","source":"epoch","metric":"epoch_osworld","value":0.721,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://os-world.github.io/"},{"modelId":"anthropic/claude-sonnet-4.5","source":"epoch","metric":"epoch_osworld","value":0.629,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://os-world.github.io/"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_osworld","value":0.23,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://os-world.github.io/"},{"modelId":"qwen/qwen2.5-vl-72b-instruct","source":"epoch","metric":"epoch_osworld","value":0.05,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://os-world.github.io/"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_osworld","value":0.663,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.anthropic.com/news/claude-opus-4-5"},{"modelId":"moonshotai/kimi-k2.5","source":"epoch","metric":"epoch_osworld","value":0.633,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://os-world.github.io/"},{"modelId":"openai/gpt-6.1-sol","source":"epoch","metric":"epoch_spireclimb","value":0.24666666666666667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-sonnet-5.5","source":"epoch","metric":"epoch_spireclimb","value":0.013333333333333334,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-luna","source":"epoch","metric":"epoch_spireclimb","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-fable-5.1","source":"epoch","metric":"epoch_spireclimb","value":0.02,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-5.5","source":"epoch","metric":"epoch_spireclimb","value":0.03333333333333333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-sol","source":"epoch","metric":"epoch_spireclimb","value":0.075,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_spireclimb","value":0.25666666666666665,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.2","source":"epoch","metric":"epoch_vpct","value":0.84,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cbrower.dev/vpct"},{"modelId":"google/gemini-3-flash-preview","source":"epoch","metric":"epoch_vpct","value":0.726,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cbrower.dev/vpct"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_vpct","value":0.66,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cbrower.dev/vpct"},{"modelId":"openai/gpt-5.1","source":"epoch","metric":"epoch_vpct","value":0.587,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cbrower.dev/vpct"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_vpct","value":0.575,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cbrower.dev/vpct"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_vpct","value":0.52,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cbrower.dev/vpct"},{"modelId":"google/gemini-2.5-pro-preview","source":"epoch","metric":"epoch_vpct","value":0.464,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cbrower.dev/vpct"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_vpct","value":0.402,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cbrower.dev/vpct"},{"modelId":"openai/gpt-4o-2024-11-20","source":"epoch","metric":"epoch_vpct","value":0.4,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cbrower.dev/vpct"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_vpct","value":0.4,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://x.com/ChaseBrowe32432/status/1993038782975951149"},{"modelId":"anthropic/claude-sonnet-4.5","source":"epoch","metric":"epoch_vpct","value":0.398,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cbrower.dev/vpct"},{"modelId":"openai/gpt-5-nano","source":"epoch","metric":"epoch_vpct","value":0.372,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cbrower.dev/vpct"},{"modelId":"openai/o1","source":"epoch","metric":"epoch_vpct","value":0.37,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cbrower.dev/vpct"},{"modelId":"anthropic/claude-opus-4.1","source":"epoch","metric":"epoch_vpct","value":0.35,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cbrower.dev/vpct"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"epoch","metric":"epoch_vpct","value":0.34,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://cbrower.dev/vpct"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"epoch","metric":"epoch_bbh","value":0.798,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arxiv.org/pdf/2412.19437"},{"modelId":"openai/gpt-4","source":"epoch","metric":"epoch_bbh","value":0.7512,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"http://arxiv.org/abs/2309.10305"},{"modelId":"openai/gpt-3.5-turbo","source":"epoch","metric":"epoch_bbh","value":0.6159,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"http://arxiv.org/abs/2309.10305"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"epoch","metric":"epoch_arc_ai2","value":0.945,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"http://arxiv.org/abs/2412.19437"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"epoch","metric":"epoch_arc_ai2","value":0.705,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"http://arxiv.org/abs/2409.12186"},{"modelId":"openai/gpt-4","source":"epoch","metric":"epoch_arc_ai2","value":0.963,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"http://arxiv.org/abs/2303.08774"},{"modelId":"openai/gpt-4","source":"epoch","metric":"epoch_hellaswag","value":0.953,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"http://arxiv.org/abs/2311.16867"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"epoch","metric":"epoch_hellaswag","value":0.848,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arxiv.org/pdf/2412.19437"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"epoch","metric":"epoch_hellaswag","value":0.83,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arxiv.org/pdf/2409.12186"},{"modelId":"openai/gpt-4","source":"epoch","metric":"epoch_winogrande","value":0.875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arxiv.org/pdf/2303.08774"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"epoch","metric":"epoch_winogrande","value":0.808,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arxiv.org/pdf/2409.12186"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"epoch","metric":"epoch_winogrande","value":0.823,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://arxiv.org/pdf/2412.19437"},{"modelId":"openai/gpt-3.5-turbo-0613","source":"epoch","metric":"epoch_winogrande","value":0.816,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"http://arxiv.org/abs/2311.16867"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"epoch","metric":"epoch_piqa","value":0.812,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"http://arxiv.org/abs/2404.14219"},{"modelId":"openai/gpt-4o-mini","source":"epoch","metric":"epoch_piqa","value":0.887,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"http://arxiv.org/abs/2404.14219"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"epoch","metric":"epoch_piqa","value":0.826,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"http://arxiv.org/abs/2412.19437"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_cl_bench_life","value":0.222,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_cl_bench_life","value":0.217,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-5.1","source":"epoch","metric":"epoch_cl_bench_life","value":0.173,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"anthropic/claude-opus-4.6","source":"epoch","metric":"epoch_cl_bench_life","value":0.17,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_cl_bench_life","value":0.169,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v4-pro","source":"epoch","metric":"epoch_cl_bench_life","value":0.135,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"moonshotai/kimi-k2.5","source":"epoch","metric":"epoch_cl_bench_life","value":0.132,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"epoch","metric":"epoch_cl_bench_life","value":0.12400000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"x-ai/grok-4.20","source":"epoch","metric":"epoch_cl_bench_life","value":0.119,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"z-ai/glm-4.7","source":"epoch","metric":"epoch_cl_bench_life","value":0.109,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"epoch","metric":"epoch_cl_bench_life","value":0.095,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"deepseek/deepseek-v3.2","source":"epoch","metric":"epoch_cl_bench_life","value":0.074,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"minimax/minimax-m2.5","source":"epoch","metric":"epoch_cl_bench_life","value":0.063,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/benchmarks"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_vending_bench_2_usd","value":15514.7,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"openai/gpt-6-sol","source":"epoch","metric":"epoch_vending_bench_2_usd","value":14427.85,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"google/gemini-4-argon","source":"epoch","metric":"epoch_vending_bench_2_usd","value":13718.16,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_vending_bench_2_usd","value":11181.87,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"anthropic/claude-sonnet-5.5","source":"epoch","metric":"epoch_vending_bench_2_usd","value":11165.28,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"anthropic/claude-opus-4.7","source":"epoch","metric":"epoch_vending_bench_2_usd","value":10936.76,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"x-ai/grok-4.7","source":"epoch","metric":"epoch_vending_bench_2_usd","value":10536.83,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_vending_bench_2_usd","value":9619.37,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"meta/muse-wonder","source":"epoch","metric":"epoch_vending_bench_2_usd","value":9432.18,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"anthropic/claude-opus-5.5","source":"epoch","metric":"epoch_vending_bench_2_usd","value":9235.25,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_vending_bench_2_usd","value":9047.03,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_vending_bench_2_usd","value":8313.78,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"z-ai/glm-5.3","source":"epoch","metric":"epoch_vending_bench_2_usd","value":8163.61,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"anthropic/claude-opus-4.6","source":"epoch","metric":"epoch_vending_bench_2_usd","value":8017.59,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_vending_bench_2_usd","value":7523.84,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_vending_bench_2_usd","value":7343.21,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"anthropic/claude-sonnet-4.6","source":"epoch","metric":"epoch_vending_bench_2_usd","value":7204.14,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"meta/muse-spark-1.1","source":"epoch","metric":"epoch_vending_bench_2_usd","value":6520.48,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"anthropic/claude-sonnet-5","source":"epoch","metric":"epoch_vending_bench_2_usd","value":6377.7,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"moonshotai/kimi-k2.6","source":"epoch","metric":"epoch_vending_bench_2_usd","value":6204.57,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_vending_bench_2_usd","value":6144.18,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"openai/gpt-5.3-codex","source":"epoch","metric":"epoch_vending_bench_2_usd","value":5940.12,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_vending_bench_2_usd","value":5787.43,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_vending_bench_2_usd","value":5680.26,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"z-ai/glm-5.1","source":"epoch","metric":"epoch_vending_bench_2_usd","value":5634.41,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"anthropic/claude-fable-5.1","source":"epoch","metric":"epoch_vending_bench_2_usd","value":5421.56,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"google/gemini-3.5-flash","source":"epoch","metric":"epoch_vending_bench_2_usd","value":5396.42,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_vending_bench_2_usd","value":5165.04,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"qwen/qwen3.6-plus","source":"epoch","metric":"epoch_vending_bench_2_usd","value":5114.87,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_vending_bench_2_usd","value":5093.79,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"moonshotai/kimi-k2.7-code","source":"epoch","metric":"epoch_vending_bench_2_usd","value":5082.94,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_vending_bench_2_usd","value":4967.06,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"x-ai/grok-4.20","source":"epoch","metric":"epoch_vending_bench_2_usd","value":4662.85,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"z-ai/glm-5","source":"epoch","metric":"epoch_vending_bench_2_usd","value":4432.12,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_vending_bench_2_usd","value":4094.71,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"x-ai/grok-4.5","source":"epoch","metric":"epoch_vending_bench_2_usd","value":3887.43,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"anthropic/claude-sonnet-4.5","source":"epoch","metric":"epoch_vending_bench_2_usd","value":3838.74,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"google/gemini-3.1-pro-preview-customtools","source":"epoch","metric":"epoch_vending_bench_2_usd","value":3774.25,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"google/gemini-3-flash-preview","source":"epoch","metric":"epoch_vending_bench_2_usd","value":3634.72,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"anthropic/claude-haiku-5.5","source":"epoch","metric":"epoch_vending_bench_2_usd","value":3602.46,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"openai/gpt-5.2","source":"epoch","metric":"epoch_vending_bench_2_usd","value":3591.33,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"deepseek/deepseek-v4-pro","source":"epoch","metric":"epoch_vending_bench_2_usd","value":3284.52,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"z-ai/glm-4.7","source":"epoch","metric":"epoch_vending_bench_2_usd","value":2376.82,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"minimax/minimax-m3","source":"epoch","metric":"epoch_vending_bench_2_usd","value":2157.77,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"openai/gpt-5.1","source":"epoch","metric":"epoch_vending_bench_2_usd","value":1473.43,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"moonshotai/kimi-k2.5","source":"epoch","metric":"epoch_vending_bench_2_usd","value":1198.46,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"deepseek/deepseek-v3.2","source":"epoch","metric":"epoch_vending_bench_2_usd","value":1034,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"google/gemini-3.1-pro-preview","source":"epoch","metric":"epoch_vending_bench_2_usd","value":911.21,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"google/gemini-2.5-pro","source":"epoch","metric":"epoch_vending_bench_2_usd","value":573.64,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"google/gemini-2.5-flash","source":"epoch","metric":"epoch_vending_bench_2_usd","value":548.84,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"epoch","metric":"epoch_vending_bench_2_usd","value":462.69,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"anthropic/claude-haiku-4.5","source":"epoch","metric":"epoch_vending_bench_2_usd","value":458.89,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"qwen/qwen3.5-27b","source":"epoch","metric":"epoch_vending_bench_2_usd","value":201.98,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"minimax/minimax-m2","source":"epoch","metric":"epoch_vending_bench_2_usd","value":160.6,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"x-ai/grok-4.3","source":"epoch","metric":"epoch_vending_bench_2_usd","value":35.26,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"epoch","metric":"epoch_vending_bench_2_usd","value":0.54,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"epoch","metric":"epoch_vending_bench_2_usd","value":-11.34,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"openai/gpt-oss-120b","source":"epoch","metric":"epoch_vending_bench_2_usd","value":-21.53,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"minimax/minimax-m2.5","source":"epoch","metric":"epoch_vending_bench_2_usd","value":-23.16,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_vending_bench_2_usd","value":-31.18,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://andonlabs.com/evals/vending-bench-2"},{"modelId":"z-ai/glm-5","source":"epoch","metric":"epoch_training_compute_flop","value":6.84e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_training_compute_flop","value":6.6e+25,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"moonshotai/kimi-k2.5","source":"epoch","metric":"epoch_training_compute_flop","value":5.8e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"deepseek/deepseek-v3.2","source":"epoch","metric":"epoch_training_compute_flop","value":4.2e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"moonshotai/kimi-k2-thinking","source":"epoch","metric":"epoch_training_compute_flop","value":4.2e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"z-ai/glm-4.7","source":"epoch","metric":"epoch_training_compute_flop","value":4.42e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"qwen/qwen3-coder","source":"epoch","metric":"epoch_training_compute_flop","value":1.575e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"z-ai/glm-4.6","source":"epoch","metric":"epoch_training_compute_flop","value":4.42e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"openai/gpt-oss-120b","source":"epoch","metric":"epoch_training_compute_flop","value":4.94e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"openai/gpt-oss-20b","source":"epoch","metric":"epoch_training_compute_flop","value":5.49e+23,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_training_compute_flop","value":2.0001e+25,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"z-ai/glm-5.3-flash","source":"epoch","metric":"epoch_training_compute_flop","value":3.24e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_training_compute_flop","value":9.4e+26,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"epoch","metric":"epoch_training_compute_flop","value":4.32e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"epoch","metric":"epoch_training_compute_flop","value":9.702e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"epoch","metric":"epoch_training_compute_flop","value":2.496e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"deepseek/deepseek-v4-pro","source":"epoch","metric":"epoch_training_compute_flop","value":9.702e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"thinkingmachines/inkling","source":"epoch","metric":"epoch_training_compute_flop","value":1.1e+25,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"epoch","metric":"epoch_training_compute_flop","value":6.6e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"z-ai/glm-4.5-air","source":"epoch","metric":"epoch_training_compute_flop","value":1.656e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"openai/gpt-6-astra-pro","source":"epoch","metric":"epoch_training_compute_flop","value":9.4e+26,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"deepseek/deepseek-v4-flash","source":"epoch","metric":"epoch_training_compute_flop","value":2.496e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"deepseek/deepseek-r1-0528","source":"epoch","metric":"epoch_training_compute_flop","value":4.020010000000001e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"epoch","metric":"epoch_training_compute_flop","value":4.752e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"z-ai/glm-4.5","source":"epoch","metric":"epoch_training_compute_flop","value":4.42e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"epoch","metric":"epoch_training_compute_flop","value":4.18e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"epoch","metric":"epoch_training_compute_flop","value":4.752e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"moonshotai/kimi-k2-0905","source":"epoch","metric":"epoch_training_compute_flop","value":2.976e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"epoch","metric":"epoch_training_compute_flop","value":3.3e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"qwen/qwen3-30b-a3b","source":"epoch","metric":"epoch_training_compute_flop","value":6.48e+23,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"meta-llama/llama-4-maverick","source":"epoch","metric":"epoch_training_compute_flop","value":2.244000000001e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"epoch","metric":"epoch_training_compute_flop","value":7.8e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"epoch","metric":"epoch_training_compute_flop","value":6.8649768e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"epoch","metric":"epoch_training_compute_flop","value":7.929e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"epoch","metric":"epoch_training_compute_flop","value":1.224e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"microsoft/phi-4","source":"epoch","metric":"epoch_training_compute_flop","value":9.3202015e+23,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"epoch","metric":"epoch_training_compute_flop","value":1.7334e+23,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"qwen/qwen-2.5-7b-instruct","source":"epoch","metric":"epoch_training_compute_flop","value":8.2188e+23,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"epoch","metric":"epoch_training_compute_flop","value":6.642e+22,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"qwen/qwen3-32b","source":"epoch","metric":"epoch_training_compute_flop","value":7.0848e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"epoch","metric":"epoch_training_compute_flop","value":6.48e+23,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"qwen/qwen3-14b","source":"epoch","metric":"epoch_training_compute_flop","value":3.1968e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"google/gemma-3-4b-it","source":"epoch","metric":"epoch_training_compute_flop","value":9.6e+22,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"google/gemma-3-12b-it","source":"epoch","metric":"epoch_training_compute_flop","value":8.64e+23,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"google/gemma-3-27b-it","source":"epoch","metric":"epoch_training_compute_flop","value":2.268e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"deepseek/deepseek-chat","source":"epoch","metric":"epoch_training_compute_flop","value":4.2e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"meta-llama/llama-4-scout","source":"epoch","metric":"epoch_training_compute_flop","value":4.08e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"google/gemma-2-27b-it","source":"epoch","metric":"epoch_training_compute_flop","value":2.106e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"amazon/nova-pro-v1","source":"epoch","metric":"epoch_training_compute_flop","value":6.000010000000001e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"epoch","metric":"epoch_training_compute_flop","value":6.804e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"xiaomi/mimo-v2.5","source":"epoch","metric":"epoch_training_compute_flop","value":4.32e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"openai/gpt-4","source":"epoch","metric":"epoch_training_compute_flop","value":2.1e+25,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"epoch","metric":"epoch_training_compute_flop","value":1.0725e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"qwen/qwen2.5-vl-72b-instruct","source":"epoch","metric":"epoch_training_compute_flop","value":7.8e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"epoch","metric":"epoch_training_compute_flop","value":3.594058e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"deepseek/deepseek-chat-v3.1","source":"epoch","metric":"epoch_training_compute_flop","value":3.594058e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"mistralai/mixtral-8x22b-instruct","source":"epoch","metric":"epoch_training_compute_flop","value":2.34e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"epoch","metric":"epoch_training_compute_flop","value":1.152e+24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/data/ai-models"},{"modelId":"anthropic/claude-opus-5.5","source":"epoch","metric":"epoch_eci","value":166.82,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"openai/gpt-6-astra","source":"epoch","metric":"epoch_eci","value":166.41,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"openai/gpt-6.1-sol","source":"epoch","metric":"epoch_eci","value":166.32,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"anthropic/claude-fable-5.1","source":"epoch","metric":"epoch_eci","value":164.65,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"google/gemini-4-argon","source":"epoch","metric":"epoch_eci","value":164.56,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"anthropic/claude-sonnet-5.5","source":"epoch","metric":"epoch_eci","value":164.45,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"anthropic/claude-opus-5","source":"epoch","metric":"epoch_eci","value":162.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"openai/gpt-6-sol","source":"epoch","metric":"epoch_eci","value":162.55,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"anthropic/claude-fable-5","source":"epoch","metric":"epoch_eci","value":162.13,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"openai/gpt-5.5-pro","source":"epoch","metric":"epoch_eci","value":161.97,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"openai/gpt-5.6-sol","source":"epoch","metric":"epoch_eci","value":161.73,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"openai/gpt-5.6-terra","source":"epoch","metric":"epoch_eci","value":159.43,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"openai/gpt-5.4-pro","source":"epoch","metric":"epoch_eci","value":159,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"anthropic/claude-haiku-5.5","source":"epoch","metric":"epoch_eci","value":158.98,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"openai/gpt-5.5","source":"epoch","metric":"epoch_eci","value":158.95,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"anthropic/claude-opus-4.8","source":"epoch","metric":"epoch_eci","value":158.26,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"moonshotai/kimi-k3","source":"epoch","metric":"epoch_eci","value":157.42,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"google/gemini-3.7-flash","source":"epoch","metric":"epoch_eci","value":157.22,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"google/gemini-3.8-flash","source":"epoch","metric":"epoch_eci","value":157.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"qwen/qwen3.8-max-0902","source":"epoch","metric":"epoch_eci","value":156.88,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"openai/gpt-5.3-codex","source":"epoch","metric":"epoch_eci","value":156.76,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"meta/muse-spark-1.3","source":"epoch","metric":"epoch_eci","value":156.76,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"openai/gpt-5.4","source":"epoch","metric":"epoch_eci","value":156.72,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"anthropic/claude-sonnet-5","source":"epoch","metric":"epoch_eci","value":156.36,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"openai/gpt-5.6-luna","source":"epoch","metric":"epoch_eci","value":156.33,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"anthropic/claude-opus-4.7","source":"epoch","metric":"epoch_eci","value":156.32,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"openai/gpt-6-luna","source":"epoch","metric":"epoch_eci","value":156.31,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"x-ai/grok-4.6","source":"epoch","metric":"epoch_eci","value":156.31,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"openai/gpt-5.2-pro","source":"epoch","metric":"epoch_eci","value":156.03,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"z-ai/glm-5.3","source":"epoch","metric":"epoch_eci","value":155.91,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"epoch","metric":"epoch_eci","value":155.57,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"epoch","metric":"epoch_eci","value":155.29,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"anthropic/claude-opus-4.6","source":"epoch","metric":"epoch_eci","value":155.27,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"meta/muse-spark-1.2","source":"epoch","metric":"epoch_eci","value":154.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"epoch","metric":"epoch_eci","value":154.49,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"google/gemini-3.5-flash","source":"epoch","metric":"epoch_eci","value":154.38,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"x-ai/grok-4.7","source":"epoch","metric":"epoch_eci","value":154.37,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"google/gemini-3.6-flash","source":"epoch","metric":"epoch_eci","value":154.24,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"meta/muse-spark-1.1","source":"epoch","metric":"epoch_eci","value":154,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"x-ai/grok-4.5","source":"epoch","metric":"epoch_eci","value":153.93,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"qwen/qwen3.7-max","source":"epoch","metric":"epoch_eci","value":153.83,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"openai/gpt-5.2","source":"epoch","metric":"epoch_eci","value":153.46,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"z-ai/glm-5.3-flash","source":"epoch","metric":"epoch_eci","value":153.23,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"anthropic/claude-sonnet-4.6","source":"epoch","metric":"epoch_eci","value":152.39,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"x-ai/grok-4.20","source":"epoch","metric":"epoch_eci","value":152.08,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"z-ai/glm-5.2","source":"epoch","metric":"epoch_eci","value":151.86,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"qwen/qwen3.8-27b","source":"epoch","metric":"epoch_eci","value":151.55,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"moonshotai/kimi-k2.6","source":"epoch","metric":"epoch_eci","value":150.92,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"openai/gpt-5-pro","source":"epoch","metric":"epoch_eci","value":150.74,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"thinkingmachines/inkling-small","source":"epoch","metric":"epoch_eci","value":150.18,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"anthropic/claude-opus-4.5","source":"epoch","metric":"epoch_eci","value":150.17,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"openai/gpt-5","source":"epoch","metric":"epoch_eci","value":150,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"z-ai/glm-5.1","source":"epoch","metric":"epoch_eci","value":149.99,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"moonshotai/kimi-k2.7-code","source":"epoch","metric":"epoch_eci","value":149.87,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"openai/gpt-5.1","source":"epoch","metric":"epoch_eci","value":149.76,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"deepseek/deepseek-v4-pro","source":"epoch","metric":"epoch_eci","value":149.19,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"openai/gpt-5.4-mini","source":"epoch","metric":"epoch_eci","value":148.77,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"thinkingmachines/inkling","source":"epoch","metric":"epoch_eci","value":148.59,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"moonshotai/kimi-k2.5","source":"epoch","metric":"epoch_eci","value":147.98,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"qwen/qwen3.6-plus","source":"epoch","metric":"epoch_eci","value":147.49,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"openai/o3-pro","source":"epoch","metric":"epoch_eci","value":147.37,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"qwen/qwen3.7-plus","source":"epoch","metric":"epoch_eci","value":147.3,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"minimax/minimax-m3","source":"epoch","metric":"epoch_eci","value":147.13,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"mistralai/mistral-large-4-0","source":"epoch","metric":"epoch_eci","value":146.9,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"openai/o3","source":"epoch","metric":"epoch_eci","value":146.87,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"anthropic/claude-sonnet-4.5","source":"epoch","metric":"epoch_eci","value":146.83,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"minimax/minimax-m2.5","source":"epoch","metric":"epoch_eci","value":146.67,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"epoch","metric":"epoch_eci","value":146.66,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"qwen/qwen3.6-27b","source":"epoch","metric":"epoch_eci","value":146.48,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"epoch","metric":"epoch_eci","value":146.32,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"openai/gpt-5.4-nano","source":"epoch","metric":"epoch_eci","value":146.12,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"deepseek/deepseek-v3.2","source":"epoch","metric":"epoch_eci","value":146.11,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"deepseek/deepseek-v4-flash","source":"epoch","metric":"epoch_eci","value":146.05,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"moonshotai/kimi-k2-thinking","source":"epoch","metric":"epoch_eci","value":145.96,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"minimax/minimax-m2.7","source":"epoch","metric":"epoch_eci","value":145.88,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"z-ai/glm-5","source":"epoch","metric":"epoch_eci","value":145.78,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"epoch","metric":"epoch_eci","value":145.77,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"openai/o4-mini","source":"epoch","metric":"epoch_eci","value":145.6,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"openai/gpt-5-mini","source":"epoch","metric":"epoch_eci","value":145.43,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"google/gemini-2.5-pro","source":"epoch","metric":"epoch_eci","value":145.31,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"google/gemini-3.5-flash-lite","source":"epoch","metric":"epoch_eci","value":145.15,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"epoch","metric":"epoch_eci","value":144.97,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"qwen/qwen3.7-flash","source":"epoch","metric":"epoch_eci","value":144.64,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"google/gemini-3.1-flash-lite","source":"epoch","metric":"epoch_eci","value":144.47,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"qwen/qwen3.6-35b-a3b","source":"epoch","metric":"epoch_eci","value":144.11,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"anthropic/claude-opus-4.1","source":"epoch","metric":"epoch_eci","value":144.09,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"z-ai/glm-4.7","source":"epoch","metric":"epoch_eci","value":143.79,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"epoch","metric":"epoch_eci","value":143.77,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"qwen/qwen3.6-flash","source":"epoch","metric":"epoch_eci","value":143.05,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"google/gemini-2.5-flash","source":"epoch","metric":"epoch_eci","value":143,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"google/gemma-4-31b-it","source":"epoch","metric":"epoch_eci","value":142.86,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"epoch","metric":"epoch_eci","value":142.48,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"anthropic/claude-haiku-4.5","source":"epoch","metric":"epoch_eci","value":142.4,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"openai/o1","source":"epoch","metric":"epoch_eci","value":141.84,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"google/gemma-4-26b-a4b-it","source":"epoch","metric":"epoch_eci","value":141.81,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"mistralai/mistral-medium-3-5","source":"epoch","metric":"epoch_eci","value":141.47,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"openai/o3-mini","source":"epoch","metric":"epoch_eci","value":140.33,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"moonshotai/kimi-k2","source":"epoch","metric":"epoch_eci","value":140.12,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"openai/gpt-oss-120b","source":"epoch","metric":"epoch_eci","value":140,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"qwen/qwen3.5-9b","source":"epoch","metric":"epoch_eci","value":139.43,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"openai/gpt-5-nano","source":"epoch","metric":"epoch_eci","value":139.33,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"qwen/qwen3-32b","source":"epoch","metric":"epoch_eci","value":138.49,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"qwen/qwen3-14b","source":"epoch","metric":"epoch_eci","value":138.22,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"openai/gpt-oss-20b","source":"epoch","metric":"epoch_eci","value":137.81,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"qwen/qwen3-30b-a3b","source":"epoch","metric":"epoch_eci","value":137.42,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"openai/gpt-4.1","source":"epoch","metric":"epoch_eci","value":136.77,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"openai/gpt-4.1-mini","source":"epoch","metric":"epoch_eci","value":135,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"mistralai/mistral-medium-3","source":"epoch","metric":"epoch_eci","value":134.06,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"google/gemini-2.5-flash-lite","source":"epoch","metric":"epoch_eci","value":133.95,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"meta-llama/llama-4-maverick","source":"epoch","metric":"epoch_eci","value":132.2,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"microsoft/phi-4","source":"epoch","metric":"epoch_eci","value":130.43,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"google/gemma-3-27b-it","source":"epoch","metric":"epoch_eci","value":130.05,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"meta-llama/llama-4-scout","source":"epoch","metric":"epoch_eci","value":129.65,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"openai/gpt-4.1-nano","source":"epoch","metric":"epoch_eci","value":129.63,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"epoch","metric":"epoch_eci","value":129,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"epoch","metric":"epoch_eci","value":127.34,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"openai/gpt-4-turbo","source":"epoch","metric":"epoch_eci","value":127.25,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"epoch","metric":"epoch_eci","value":127.08,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"openai/gpt-4o-mini","source":"epoch","metric":"epoch_eci","value":126.58,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"epoch","metric":"epoch_eci","value":125.94,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"openai/gpt-4","source":"epoch","metric":"epoch_eci","value":125.88,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"amazon/nova-pro-v1","source":"epoch","metric":"epoch_eci","value":123.8,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"google/gemma-3-12b-it","source":"epoch","metric":"epoch_eci","value":123.49,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"google/gemma-2-27b-it","source":"epoch","metric":"epoch_eci","value":122.1,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"mistralai/mixtral-8x22b-instruct","source":"epoch","metric":"epoch_eci","value":122.05,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"mistralai/mistral-large","source":"epoch","metric":"epoch_eci","value":122.03,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"epoch","metric":"epoch_eci","value":119.52,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"mistralai/mistral-nemo","source":"epoch","metric":"epoch_eci","value":118.71,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"qwen/qwen-2.5-7b-instruct","source":"epoch","metric":"epoch_eci","value":118.53,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"epoch","metric":"epoch_eci","value":116.61,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"google/gemma-3-4b-it","source":"epoch","metric":"epoch_eci","value":116.01,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"epoch","metric":"epoch_eci","value":102.04,"unit":"points","observedAt":"2026-10-20","sourceUrl":"https://epoch.ai/eci"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_livecodebench","value":0.9052,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":59.74,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_livecodebench","value":0.8978,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":118.53,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_livecodebench","value":0.8948,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":24.07,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_livecodebench","value":0.8903,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":59.22,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_livecodebench","value":0.8865000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":14.53,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_livecodebench","value":0.8848,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":88.89,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_livecodebench","value":0.8822,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":118.4,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_livecodebench","value":0.8808,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":31.88,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-5.2-codex","source":"vals-more","metric":"vals_livecodebench","value":0.8798999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-5.2-codex","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":168,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_livecodebench","value":0.8785,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":338,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_livecodebench","value":0.8782,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":160,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_livecodebench","value":0.8759999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":64.37,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_livecodebench","value":0.8753,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":273,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_livecodebench","value":0.8748,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":716,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_livecodebench","value":0.8734999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":589,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-5.3-codex","source":"vals-more","metric":"vals_livecodebench","value":0.8731,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-5.3-codex","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":133,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_livecodebench","value":0.8726,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":127,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_livecodebench","value":0.8719,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":200,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_livecodebench","value":0.8706,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":192,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_livecodebench","value":0.8676999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":529,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-5-mini","source":"vals-more","metric":"vals_livecodebench","value":0.8661,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-5-mini","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":33.67,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-5.1","source":"vals-more","metric":"vals_livecodebench","value":0.8649,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-5.1","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":141,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"vals-more","metric":"vals_livecodebench","value":0.8598,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":161,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_livecodebench","value":0.8595,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":476,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_livecodebench","value":0.8593000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":302,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_livecodebench","value":0.8593000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":44.33,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-5","source":"vals-more","metric":"vals_livecodebench","value":0.8591,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-5","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":150,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_livecodebench","value":0.8591,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":113.25,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_livecodebench","value":0.8559,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":91.93,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-5.1-codex","source":"vals-more","metric":"vals_livecodebench","value":0.8554999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-5.1-codex","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":234,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_livecodebench","value":0.8552,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":258,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-5.2","source":"vals-more","metric":"vals_livecodebench","value":0.8536,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-5.2","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":152,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"vals-more","metric":"vals_livecodebench","value":0.8533,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":247,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_livecodebench","value":0.853,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":167,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_livecodebench","value":0.8506999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":462,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"anthropic/claude-opus-4.6","source":"vals-more","metric":"vals_livecodebench","value":0.8468000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"anthropic/claude-opus-4.6","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":324,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_livecodebench","value":0.8449,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":3249,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_livecodebench","value":0.8427,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":76.09,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_livecodebench","value":0.8414,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":209,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_livecodebench","value":0.8401000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":60.09,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_livecodebench","value":0.84,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":149,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_livecodebench","value":0.8399,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":60.4,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/o3","source":"vals-more","metric":"vals_livecodebench","value":0.8391,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/o3","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":63.95,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_livecodebench","value":0.8387,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":200,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-more","metric":"vals_livecodebench","value":0.8367,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":164,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-5.1-codex-max","source":"vals-more","metric":"vals_livecodebench","value":0.8356,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-5.1-codex-max","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":66.2,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"vals-more","metric":"vals_livecodebench","value":0.8328,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":209,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-oss-120b","source":"vals-more","metric":"vals_livecodebench","value":0.8323,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-oss-120b","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":81.7,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_livecodebench","value":0.826,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":56.51,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_livecodebench","value":0.8243,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":77.02,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"z-ai/glm-4.7","source":"vals-more","metric":"vals_livecodebench","value":0.8223,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"z-ai/glm-4.7","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":393,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/o4-mini","source":"vals-more","metric":"vals_livecodebench","value":0.8220999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/o4-mini","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":32.84,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_livecodebench","value":0.8215,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":367,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_livecodebench","value":0.8209000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":295,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"moonshotai/kimi-k2.7-code","source":"vals-more","metric":"vals_livecodebench","value":0.8205,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"moonshotai/kimi-k2.7-code","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":214,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"z-ai/glm-5","source":"vals-more","metric":"vals_livecodebench","value":0.8187000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"z-ai/glm-5","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":290,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"minimax/minimax-m2.1","source":"vals-more","metric":"vals_livecodebench","value":0.8176000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"minimax/minimax-m2.1","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":246,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_livecodebench","value":0.8151,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":108.61,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_livecodebench","value":0.8147,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":189,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_livecodebench","value":0.8138,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":226,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_livecodebench","value":0.8134999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":271,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"z-ai/glm-4.6","source":"vals-more","metric":"vals_livecodebench","value":0.8104,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"z-ai/glm-4.6","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":236,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"deepseek/deepseek-v3.2","source":"vals-more","metric":"vals_livecodebench","value":0.8069,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"deepseek/deepseek-v3.2","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":254,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_livecodebench","value":0.8053,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":247,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_livecodebench","value":0.8051,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":302,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-oss-20b","source":"vals-more","metric":"vals_livecodebench","value":0.8039000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-oss-20b","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":109.45,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_livecodebench","value":0.8012,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":30.75,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_livecodebench","value":0.7993000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":319,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"minimax/minimax-m2.5","source":"vals-more","metric":"vals_livecodebench","value":0.7920999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"minimax/minimax-m2.5","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":312,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"google/gemini-2.5-pro-preview","source":"vals-more","metric":"vals_livecodebench","value":0.7916,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"google/gemini-2.5-pro-preview","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":165,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_livecodebench","value":0.7901,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":21.08,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-more","metric":"vals_livecodebench","value":0.73,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":109.55,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/o3-mini","source":"vals-more","metric":"vals_livecodebench","value":0.7148,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/o3-mini","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":53.8,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"google/gemini-2.5-flash-lite","source":"vals-more","metric":"vals_livecodebench","value":0.7139,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"google/gemini-2.5-flash-lite","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":38.7,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"moonshotai/kimi-k2","source":"vals-more","metric":"vals_livecodebench","value":0.7045,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"moonshotai/kimi-k2","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":66.65,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-5-nano","source":"vals-more","metric":"vals_livecodebench","value":0.7021999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-5-nano","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":136,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_livecodebench","value":0.695,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":532,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"z-ai/glm-4.5","source":"vals-more","metric":"vals_livecodebench","value":0.6745,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"z-ai/glm-4.5","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":391,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"anthropic/claude-opus-4.1","source":"vals-more","metric":"vals_livecodebench","value":0.6646,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"anthropic/claude-opus-4.1","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":92.17,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"vals-more","metric":"vals_livecodebench","value":0.6548,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":26.93,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"moonshotai/kimi-k2-thinking","source":"vals-more","metric":"vals_livecodebench","value":0.6315,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"moonshotai/kimi-k2-thinking","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":1151,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-4.1-mini","source":"vals-more","metric":"vals_livecodebench","value":0.5816,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-4.1-mini","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":27.59,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"mistralai/mistral-large-2512","source":"vals-more","metric":"vals_livecodebench","value":0.5534,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"mistralai/mistral-large-2512","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":28.89,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-4.1","source":"vals-more","metric":"vals_livecodebench","value":0.5467,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-4.1","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":30.57,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"mistralai/devstral-2512","source":"vals-more","metric":"vals_livecodebench","value":0.5184000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"mistralai/devstral-2512","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":87.57,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/o1","source":"vals-more","metric":"vals_livecodebench","value":0.5025999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/o1","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":92.08,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"meta-llama/llama-4-maverick","source":"vals-more","metric":"vals_livecodebench","value":0.4725,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"meta-llama/llama-4-maverick","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":9.44,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"mistralai/mistral-medium-3.1","source":"vals-more","metric":"vals_livecodebench","value":0.4484,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"mistralai/mistral-medium-3.1","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":12.48,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-4o-2024-11-20","source":"vals-more","metric":"vals_livecodebench","value":0.43439999999999995,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-4o-2024-11-20","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":4.35,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-4.1-nano","source":"vals-more","metric":"vals_livecodebench","value":0.42719999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-4.1-nano","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":11.8,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_livecodebench","value":0.4117,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":81.56,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"meta-llama/llama-4-scout","source":"vals-more","metric":"vals_livecodebench","value":0.38539999999999996,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"meta-llama/llama-4-scout","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":16.76,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"mistralai/mistral-large","source":"vals-more","metric":"vals_livecodebench","value":0.3709,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"mistralai/mistral-large","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":5.35,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"cohere/command-a","source":"vals-more","metric":"vals_livecodebench","value":0.3507,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"cohere/command-a","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":11.75,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-4o-mini","source":"vals-more","metric":"vals_livecodebench","value":0.2642,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"openai/gpt-4o-mini","source":"vals-more","metric":"vals_livecodebench_latency_seconds","value":7.36,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/lcb"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_swe_bench","value":0.97,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":1.29,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":577,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_swe_bench","value":0.9640000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.1,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":240,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_swe_bench","value":0.9620000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":1.15,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":182,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_swe_bench","value":0.956,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.78,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":604,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_swe_bench","value":0.9540000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.4,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":180,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_swe_bench","value":0.9540000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.34,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":841,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_swe_bench","value":0.95,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":2.05,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":356,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_swe_bench","value":0.934,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.76,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":619,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_swe_bench","value":0.93,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.04,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":201,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_swe_bench","value":0.92,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.02,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":3840,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_swe_bench","value":0.888,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.01,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":202,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_swe_bench","value":0.8859999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":1.92,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":567,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_swe_bench","value":0.866,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.54,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":200,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_swe_bench","value":0.866,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.55,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":487,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_swe_bench","value":0.86,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":1.08,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":600,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_swe_bench","value":0.856,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":1.13,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":2502,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_swe_bench","value":0.828,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.71,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":670,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_swe_bench","value":0.826,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":1.36,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":426,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_swe_bench","value":0.8220000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.13,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":245,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_swe_bench","value":0.82,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.35,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":209,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_swe_bench","value":0.82,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":2.42,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":442,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_swe_bench","value":0.8079999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":1.44,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":350,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_swe_bench","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":2.19,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":683,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_swe_bench","value":0.7959999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":1.19,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":788,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_swe_bench","value":0.7959999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":1.49,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":962,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_swe_bench","value":0.7879999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.95,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":254,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_swe_bench","value":0.7879999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.78,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":312,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_swe_bench","value":0.782,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.8,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":307,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-opus-4.6","source":"vals-more","metric":"vals_swe_bench","value":0.782,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-opus-4.6","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":1.22,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-opus-4.6","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":351,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"moonshotai/kimi-k2.7-code","source":"vals-more","metric":"vals_swe_bench","value":0.782,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"moonshotai/kimi-k2.7-code","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.27,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"moonshotai/kimi-k2.7-code","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":897,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.3-codex","source":"vals-more","metric":"vals_swe_bench","value":0.78,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.3-codex","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.46,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.3-codex","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":247,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_swe_bench","value":0.7759999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.59,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":394,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_swe_bench","value":0.774,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":1.3,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":512,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_swe_bench","value":0.774,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.44,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":635,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-more","metric":"vals_swe_bench","value":0.764,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":1.05,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":321,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_swe_bench","value":0.764,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.46,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":527,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_swe_bench","value":0.762,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.27,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":520,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.2","source":"vals-more","metric":"vals_swe_bench","value":0.758,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.2","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":1.45,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.2","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":640,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_swe_bench","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.28,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":285,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_swe_bench","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.31,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":440,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_swe_bench","value":0.75,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.42,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":726,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"minimax/minimax-m2.1","source":"vals-more","metric":"vals_swe_bench","value":0.748,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"minimax/minimax-m2.1","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.44,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"minimax/minimax-m2.1","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":386,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"minimax/minimax-m2.5","source":"vals-more","metric":"vals_swe_bench","value":0.742,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"minimax/minimax-m2.5","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.46,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"minimax/minimax-m2.5","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":403,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_swe_bench","value":0.74,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.02,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":471,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_swe_bench","value":0.738,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.47,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":886,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_swe_bench","value":0.7340000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.87,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":424,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_swe_bench","value":0.73,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.51,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":326,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.2-codex","source":"vals-more","metric":"vals_swe_bench","value":0.7240000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.2-codex","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.31,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.2-codex","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":188,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_swe_bench","value":0.722,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.52,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":135,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_swe_bench","value":0.7140000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.22,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":117.77,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"z-ai/glm-5","source":"vals-more","metric":"vals_swe_bench","value":0.7140000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"z-ai/glm-5","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.45,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"z-ai/glm-5","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":514,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"vals-more","metric":"vals_swe_bench","value":0.7120000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.96,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":496,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_swe_bench","value":0.71,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.01,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":244,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_swe_bench","value":0.7,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.17,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":339,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-more","metric":"vals_swe_bench","value":0.7,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.81,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":361,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"qwen/qwen3.6-27b","source":"vals-more","metric":"vals_swe_bench","value":0.7,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"qwen/qwen3.6-27b","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.91,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"qwen/qwen3.6-27b","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":1029,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_swe_bench","value":0.698,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.1,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":263,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.1","source":"vals-more","metric":"vals_swe_bench","value":0.698,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.1","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.71,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.1","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":501,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"z-ai/glm-4.7","source":"vals-more","metric":"vals_swe_bench","value":0.6940000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"z-ai/glm-4.7","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.2,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"z-ai/glm-4.7","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":366,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5","source":"vals-more","metric":"vals_swe_bench","value":0.69,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.27,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":233,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"vals-more","metric":"vals_swe_bench","value":0.69,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":283,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_swe_bench","value":0.688,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":3.23,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":976,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v3.2","source":"vals-more","metric":"vals_swe_bench","value":0.6759999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v3.2","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.67,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v3.2","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":533,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_swe_bench","value":0.6659999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.37,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":242,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_swe_bench","value":0.664,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":4,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":1144,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_swe_bench","value":0.652,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.03,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":196,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"vals-more","metric":"vals_swe_bench","value":0.644,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.26,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":363,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_swe_bench","value":0.628,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.11,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":133,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"mistralai/devstral-2512","source":"vals-more","metric":"vals_swe_bench","value":0.628,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"mistralai/devstral-2512","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.75,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"mistralai/devstral-2512","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":244,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5-mini","source":"vals-more","metric":"vals_swe_bench","value":0.608,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5-mini","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.05,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5-mini","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":187,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"moonshotai/kimi-k2-thinking","source":"vals-more","metric":"vals_swe_bench","value":0.602,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"moonshotai/kimi-k2-thinking","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.37,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"moonshotai/kimi-k2-thinking","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":1632,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-2.5-pro","source":"vals-more","metric":"vals_swe_bench","value":0.544,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-2.5-pro","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.35,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-2.5-pro","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":208,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"vals-more","metric":"vals_swe_bench","value":0.528,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.03,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":925,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"mistralai/mistral-large-2512","source":"vals-more","metric":"vals_swe_bench","value":0.414,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"mistralai/mistral-large-2512","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.32,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"mistralai/mistral-large-2512","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":187,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-oss-120b","source":"vals-more","metric":"vals_swe_bench","value":0.336,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-oss-120b","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.17,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-oss-120b","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":256,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"cohere/command-a","source":"vals-more","metric":"vals_swe_bench","value":0.078,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"cohere/command-a","source":"vals-more","metric":"vals_swe_bench_cost_per_test_usd","value":0.21,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"cohere/command-a","source":"vals-more","metric":"vals_swe_bench_duration_seconds","value":228,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_terminal_bench_4","value":0.6515000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":13.2,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":3840,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_terminal_bench_4","value":0.6414,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":16.51,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":4920,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_terminal_bench_4","value":0.596,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":9.58,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":2142,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_terminal_bench_4","value":0.5808,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":17.18,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":3600,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_terminal_bench_4","value":0.5758,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":17.64,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":3215,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_terminal_bench_4","value":0.5505,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":1.72,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":2712,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_terminal_bench_4","value":0.5353,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":18.6,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":4020,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_terminal_bench_4","value":0.4949,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":14.66,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":3281,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_terminal_bench_4","value":0.44439999999999996,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":5.79,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":2096,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_terminal_bench_4","value":0.41409999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":30.34,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":4080,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_terminal_bench_4","value":0.3889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":9.37,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":4980,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_terminal_bench_4","value":0.3788,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":7.98,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":2026,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_terminal_bench_4","value":0.3737,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":1.22,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":3660,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_terminal_bench_4","value":0.3636,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":3.12,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":3116,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_terminal_bench_4","value":0.34340000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":10.63,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":8880,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"vals-more","metric":"vals_terminal_bench_4","value":0.3182,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":0.54,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":2470,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_terminal_bench_4","value":0.3182,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":3.11,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":7080,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_terminal_bench_4","value":0.3131,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":0.5,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":9720,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_terminal_bench_4","value":0.2879,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":18.01,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":3008,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_terminal_bench_4","value":0.2778,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":10.25,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":6000,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_terminal_bench_4","value":0.24239999999999998,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":0.22,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":8700,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_terminal_bench_4","value":0.2323,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":17.14,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":4260,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_terminal_bench_4","value":0.2273,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":5.6,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":1889,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_terminal_bench_4","value":0.2071,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":19.48,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":6900,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_terminal_bench_4","value":0.19699999999999998,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":0.5,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":2902,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_terminal_bench_4","value":0.19699999999999998,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":8.65,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":6420,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_terminal_bench_4","value":0.1869,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":0.77,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":6360,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_terminal_bench_4","value":0.17170000000000002,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":5.06,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":1765,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_terminal_bench_4","value":0.17170000000000002,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":12.48,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":11340,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_terminal_bench_4","value":0.1414,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":3.31,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":5520,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_terminal_bench_4","value":0.1364,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":0.35,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":1966,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_terminal_bench_4","value":0.12119999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":8.71,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":5040,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_terminal_bench_4","value":0.1162,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":0.73,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":2155,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_terminal_bench_4","value":0.11109999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":3.45,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":5160,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_terminal_bench_4","value":0.1061,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":26.05,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":6300,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_terminal_bench_4","value":0.1061,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":7.04,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":7140,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_terminal_bench_4","value":0.0859,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":5.52,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":2023,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_terminal_bench_4","value":0.0808,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":2.1,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":7800,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"meta/muse-spark-open","source":"vals-more","metric":"vals_terminal_bench_4","value":0.06570000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"meta/muse-spark-open","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":7.26,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"meta/muse-spark-open","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":7440,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_terminal_bench_4","value":0.060599999999999994,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":5.98,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":4260,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_terminal_bench_4","value":0.060599999999999994,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":4.14,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":4680,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_terminal_bench_4","value":0.0252,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":4.11,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":1124,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_terminal_bench_4","value":0.0252,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":1.44,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":1770,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_terminal_bench_4","value":0.0101,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":7.23,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":4560,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_terminal_bench_4","value":0.0051,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":2.5,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":1379,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_terminal_bench_4","value":0.0051,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":0.23,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":7620,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_terminal_bench_4","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":0.32,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":705,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_terminal_bench_4","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_terminal_bench_4_cost_per_test_usd","value":0.37,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_terminal_bench_4_duration_seconds","value":914,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-4","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_vibe_code","value":0.9239,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":31.25,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":3660,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_vibe_code","value":0.9190999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":8.11,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":2248,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_vibe_code","value":0.9044,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":6.07,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":2076,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_vibe_code","value":0.9035,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":41.71,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":3720,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_vibe_code","value":0.9029,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":57.92,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":5760,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_vibe_code","value":0.9026000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":33.37,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":3460,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_vibe_code","value":0.8959,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":38.51,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":2344,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_vibe_code","value":0.8893000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":6.23,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":4500,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_vibe_code","value":0.884,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":33.88,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":5280,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_vibe_code","value":0.8782,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":26.36,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":2336,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"vals-more","metric":"vals_vibe_code","value":0.8773000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":0.58,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":974,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_vibe_code","value":0.8617,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":15.83,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":2147,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_vibe_code","value":0.8522,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":1.04,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":3660,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_vibe_code","value":0.8497,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":10.01,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":999,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_vibe_code","value":0.8473999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":0.41,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":928,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_vibe_code","value":0.8387,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":8.56,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":2358,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_vibe_code","value":0.8309000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":1.8,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":350,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_vibe_code","value":0.8286,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":2.1,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":774,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_vibe_code","value":0.8271999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":26.88,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":4560,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_vibe_code","value":0.823,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":0.36,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":3960,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_vibe_code","value":0.8165,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":1.35,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":2220,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_vibe_code","value":0.8133,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":25.39,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":4020,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_vibe_code","value":0.805,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":33.4,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":2033,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_vibe_code","value":0.7909999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":1.53,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":1195,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_vibe_code","value":0.7896,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":0.56,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":3013,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_vibe_code","value":0.7865000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":6.87,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":519,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_vibe_code","value":0.784,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":39.46,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":10380,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_vibe_code","value":0.7813,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":12.45,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":3840,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_vibe_code","value":0.7748,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":2.18,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":2493,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_vibe_code","value":0.7706000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":0.73,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":1552,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_vibe_code","value":0.7624,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":4.88,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":1530,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"meta/muse-spark-open","source":"vals-more","metric":"vals_vibe_code","value":0.7619,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"meta/muse-spark-open","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":1.66,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"meta/muse-spark-open","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":1869,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_vibe_code","value":0.7474,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":0.91,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":2242,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_vibe_code","value":0.7459,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":7.89,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":1152,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_vibe_code","value":0.7216,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":0.92,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":615,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_vibe_code","value":0.71,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":21.41,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":2142,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_vibe_code","value":0.7040000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":5.86,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":5460,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_vibe_code","value":0.7039,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":4.83,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":1423,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_vibe_code","value":0.6984999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":16.66,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":1912,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_vibe_code","value":0.69,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":4.1,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":830,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_vibe_code","value":0.6742,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":10.69,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":5160,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_vibe_code","value":0.6485,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":23.46,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":2619,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_vibe_code","value":0.647,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":8.24,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":10140,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_vibe_code","value":0.64,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":3.04,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":1523,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_vibe_code","value":0.6396000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":8.49,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":3720,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.3-codex","source":"vals-more","metric":"vals_vibe_code","value":0.6177,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.3-codex","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":11.91,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.3-codex","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":4560,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-opus-4.6","source":"vals-more","metric":"vals_vibe_code","value":0.5757,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-opus-4.6","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":8.69,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-opus-4.6","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":1279,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_vibe_code","value":0.5577000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"Claude Code"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":7.35,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"Claude Code"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":2982,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"Claude Code"},{"modelId":"openai/gpt-5.2","source":"vals-more","metric":"vals_vibe_code","value":0.535,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.2","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":17.75,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.2","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":4980,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_vibe_code","value":0.4993,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":2.21,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":3419,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_vibe_code","value":0.4868,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":2.54,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":893,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_vibe_code","value":0.4797,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":1.19,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":2055,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_vibe_code","value":0.4767,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":11.4,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":4680,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_vibe_code","value":0.4757,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":6.45,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":5100,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"moonshotai/kimi-k2.7-code","source":"vals-more","metric":"vals_vibe_code","value":0.4721,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"moonshotai/kimi-k2.7-code","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":3.84,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"moonshotai/kimi-k2.7-code","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":10320,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"qwen/qwen3.7-plus","source":"vals-more","metric":"vals_vibe_code","value":0.4639,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"qwen/qwen3.7-plus","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":1.08,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"qwen/qwen3.7-plus","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":2232,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_vibe_code","value":0.4217,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":0.07,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":1580,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.2-codex","source":"vals-more","metric":"vals_vibe_code","value":0.3791,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.2-codex","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":4.15,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.2-codex","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":1935,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_vibe_code","value":0.3789,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":1.93,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":2968,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_vibe_code","value":0.3716,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":0.83,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":502,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_vibe_code","value":0.3411,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":0.17,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":2404,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_vibe_code","value":0.32030000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":3.83,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":1212,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_vibe_code","value":0.3146,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":2.89,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":2015,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_vibe_code","value":0.30760000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":2.35,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":5040,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_vibe_code","value":0.261,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":1.28,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":3276,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_vibe_code","value":0.2557,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":5.45,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":2290,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.1","source":"vals-more","metric":"vals_vibe_code","value":0.24609999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.1","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":2.57,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.1","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":1836,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"z-ai/glm-5","source":"vals-more","metric":"vals_vibe_code","value":0.2336,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"z-ai/glm-5","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":40.27,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"z-ai/glm-5","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":13440,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-more","metric":"vals_vibe_code","value":0.2262,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":6.66,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":2962,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.1-codex-max","source":"vals-more","metric":"vals_vibe_code","value":0.2217,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.1-codex-max","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":7.32,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.1-codex-max","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":31200,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-more","metric":"vals_vibe_code","value":0.20629999999999998,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":32.87,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":2283,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_vibe_code","value":0.20199999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":0.94,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":807,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5","source":"vals-more","metric":"vals_vibe_code","value":0.2009,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":1.53,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":1852,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_vibe_code","value":0.19399999999999998,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":1.28,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":589,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_vibe_code","value":0.19210000000000002,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":1.61,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":1105,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_vibe_code","value":0.1905,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":0.43,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":2949,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_vibe_code","value":0.1754,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":0.88,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":2570,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"vals-more","metric":"vals_vibe_code","value":0.1574,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":3.8,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":3016,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"minimax/minimax-m2.5","source":"vals-more","metric":"vals_vibe_code","value":0.1485,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"minimax/minimax-m2.5","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":2.2,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"minimax/minimax-m2.5","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":3066,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5-mini","source":"vals-more","metric":"vals_vibe_code","value":0.1417,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5-mini","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":0.25,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5-mini","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":698,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"x-ai/grok-build-0.1","source":"vals-more","metric":"vals_vibe_code","value":0.1335,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"Grok Build"},{"modelId":"x-ai/grok-build-0.1","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":395,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"Grok Build"},{"modelId":"openai/gpt-5.1-codex","source":"vals-more","metric":"vals_vibe_code","value":0.13119999999999998,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.1-codex","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":3.8,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"openai/gpt-5.1-codex","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":3026,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"qwen/qwen3.6-27b","source":"vals-more","metric":"vals_vibe_code","value":0.11939999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"qwen/qwen3.6-27b","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":4.66,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"qwen/qwen3.6-27b","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":9780,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_vibe_code","value":0.1193,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":2.82,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":1377,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_vibe_code","value":0.1139,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":1.31,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":776,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"vals-more","metric":"vals_vibe_code","value":0.0764,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":2217,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"deepseek/deepseek-v3.2","source":"vals-more","metric":"vals_vibe_code","value":0.051100000000000007,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"deepseek/deepseek-v3.2","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":2.47,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"deepseek/deepseek-v3.2","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":3366,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_vibe_code","value":0.0406,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":0.77,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":302,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_vibe_code","value":0.0368,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":0.38,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":193,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"z-ai/glm-4.6","source":"vals-more","metric":"vals_vibe_code","value":0.030899999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"z-ai/glm-4.6","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":10.85,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"z-ai/glm-4.6","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":10020,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_vibe_code","value":0.0291,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":0.29,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":1006,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_vibe_code","value":0.028900000000000002,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":16.74,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":2471,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"google/gemini-2.5-pro","source":"vals-more","metric":"vals_vibe_code","value":0.004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"google/gemini-2.5-pro","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":1.22,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"google/gemini-2.5-pro","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":2097,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_vibe_code","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":0.51,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":573,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"vals-more","metric":"vals_vibe_code","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":0.13,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":960,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"mistralai/mistral-small-2603","source":"vals-more","metric":"vals_vibe_code","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"mistralai/mistral-small-2603","source":"vals-more","metric":"vals_vibe_code_cost_per_test_usd","value":6.47,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"mistralai/mistral-small-2603","source":"vals-more","metric":"vals_vibe_code_duration_seconds","value":1815,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","setting":"OpenHands"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_code_migration","value":0.6983,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":75.83,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":12000,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_code_migration","value":0.6817,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":57.82,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":7920,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_code_migration","value":0.6774,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":44.36,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":3510,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_code_migration","value":0.6665000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":112.97,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":11940,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_code_migration","value":0.6512,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":6.51,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":5760,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_code_migration","value":0.6255,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":69.54,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":10260,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_code_migration","value":0.5747,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":60.51,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":10260,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_code_migration","value":0.5720000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":15.68,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":5160,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_code_migration","value":0.5506,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":112.1,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":6540,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_code_migration","value":0.5461,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":70.97,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":15600,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_code_migration","value":0.5292,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":24.54,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":3552,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_code_migration","value":0.478,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":8.13,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":2914,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_code_migration","value":0.4743,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":3.41,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":7980,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_code_migration","value":0.4725,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":30.51,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":4500,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_code_migration","value":0.4562,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":0.94,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":6300,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_code_migration","value":0.45159999999999995,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":6.44,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":1895,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_code_migration","value":0.4482,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":36.55,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":4140,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_code_migration","value":0.4457,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":14.58,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":5400,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_code_migration","value":0.4457,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":6.23,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":4980,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_code_migration","value":0.44549999999999995,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":1.88,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":3515,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_code_migration","value":0.4439,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":35.31,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":7020,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_code_migration","value":0.4422,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":24.91,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":13620,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"vals-more","metric":"vals_code_migration","value":0.4421,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":1.86,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":7860,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_code_migration","value":0.4388,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":36.39,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":4320,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_code_migration","value":0.4301,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":0.69,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":10140,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_code_migration","value":0.4255,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":0.6,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":3023,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_code_migration","value":0.4154,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":18.58,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":12720,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_code_migration","value":0.4093,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":0.49,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":11520,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_code_migration","value":0.39890000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":38.51,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":6000,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_code_migration","value":0.3898,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":7.61,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":12840,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_code_migration","value":0.38630000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":3.61,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":7680,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_code_migration","value":0.3787,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":12.64,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":6840,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_code_migration","value":0.366,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":3.37,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":1409,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_code_migration","value":0.3655,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":18.49,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":9420,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_code_migration","value":0.34979999999999994,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":7.76,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":2146,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_code_migration","value":0.348,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":21.46,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":9540,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_code_migration","value":0.3251,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":51.11,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":14940,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_code_migration","value":0.3111,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":4.56,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":2351,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_code_migration","value":0.3093,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":8.93,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":5400,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_code_migration","value":0.3056,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":47.89,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":17460,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_code_migration","value":0.2995,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":3.78,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":1867,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_code_migration","value":0.2777,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":5.11,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":5400,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_code_migration","value":0.2758,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":4.62,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":4080,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_code_migration","value":0.2675,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":5.73,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":1168,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_code_migration","value":0.262,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":1.07,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":1738,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_code_migration","value":0.2577,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":5.7,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":3502,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"moonshotai/kimi-k2.7-code","source":"vals-more","metric":"vals_code_migration","value":0.2539,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"moonshotai/kimi-k2.7-code","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":5.04,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"moonshotai/kimi-k2.7-code","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":5940,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_code_migration","value":0.2396,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":10.54,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":16080,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_code_migration","value":0.21559999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":0.24,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":2933,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"meta/muse-spark-open","source":"vals-more","metric":"vals_code_migration","value":0.21170000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"meta/muse-spark-open","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":9.04,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"meta/muse-spark-open","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":6780,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_code_migration","value":0.2052,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":3.13,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":12360,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_code_migration","value":0.1993,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":7.07,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":4440,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_code_migration","value":0.17309999999999998,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":1.61,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":721,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_code_migration","value":0.161,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":13.87,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":15480,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_code_migration","value":0.1447,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":0.42,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":1594,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_code_migration","value":0.1423,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":0.1,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":2275,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_code_migration","value":0.1416,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":21.68,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":17160,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_code_migration","value":0.1368,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":0.6,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":1233,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_code_migration","value":0.1307,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":1.93,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":1532,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_code_migration","value":0.1294,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":1.95,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":1733,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"qwen/qwen3.7-plus","source":"vals-more","metric":"vals_code_migration","value":0.1286,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"qwen/qwen3.7-plus","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":0.42,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"qwen/qwen3.7-plus","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":2147,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_code_migration","value":0.11789999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":3.01,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":1774,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_code_migration","value":0.111,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":4.78,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":1790,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_code_migration","value":0.08689999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":0.59,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":1259,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_code_migration","value":0.0755,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":0.98,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":594,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_code_migration","value":0.0696,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":0.93,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":3840,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_code_migration","value":0.0679,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":0.42,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":180,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_code_migration","value":0.0639,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":0.34,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":284,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_code_migration","value":0.061500000000000006,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":0.53,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":1322,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_code_migration","value":0.0513,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":18.62,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":13080,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"vals-more","metric":"vals_code_migration","value":0.049100000000000005,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":5460,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_code_migration","value":0.0461,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":0.05,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":92.63,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_code_migration","value":0.0452,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":0.63,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":974,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"vals-more","metric":"vals_code_migration","value":0.029500000000000002,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":0.27,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":2605,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_code_migration","value":0.0031,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":0.29,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":374,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_code_migration","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_code_migration_cost_per_test_usd","value":0.06,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_code_migration_duration_seconds","value":17940,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/code-migration"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_programbench","value":0.185,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":68.05,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_programbench_duration_seconds","value":8640,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_programbench","value":0.07,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":58.52,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_programbench_duration_seconds","value":8820,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_programbench","value":0.065,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":35.86,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_programbench_duration_seconds","value":7620,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_programbench","value":0.055,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":11.57,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_programbench_duration_seconds","value":1622,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_programbench","value":0.03,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":2.87,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_programbench_duration_seconds","value":4200,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_programbench","value":0.03,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":60.29,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_programbench_duration_seconds","value":10500,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_programbench","value":0.025,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":17.66,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_programbench_duration_seconds","value":4260,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_programbench","value":0.025,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":6.83,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_programbench_duration_seconds","value":4380,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_programbench","value":0.02,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":75.68,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_programbench_duration_seconds","value":9420,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_programbench","value":0.02,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":11.67,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_programbench_duration_seconds","value":2771,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_programbench","value":0.02,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":70.48,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_programbench_duration_seconds","value":20520,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_programbench","value":0.015,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":15.29,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_programbench_duration_seconds","value":1764,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_programbench","value":0.015,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":21.96,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_programbench_duration_seconds","value":15360,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_programbench","value":0.01,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":16.76,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_programbench_duration_seconds","value":16020,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_programbench","value":0.01,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":31.27,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_programbench_duration_seconds","value":5520,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_programbench","value":0.01,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":10.93,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_programbench_duration_seconds","value":2799,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_programbench","value":0.005,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":46.49,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_programbench_duration_seconds","value":13080,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_programbench","value":0.005,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":0.47,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_programbench_duration_seconds","value":12120,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_programbench","value":0.005,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":0.9,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_programbench_duration_seconds","value":3720,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_programbench","value":0.005,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":5.38,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_programbench_duration_seconds","value":2016,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_programbench","value":0.005,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":11.56,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_programbench_duration_seconds","value":4140,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_programbench","value":0.005,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":0.73,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_programbench_duration_seconds","value":10800,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_programbench","value":0.005,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":6.95,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_programbench_duration_seconds","value":1323,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_programbench","value":0.005,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":12.58,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_programbench_duration_seconds","value":7560,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_programbench","value":0.005,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":0.18,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_programbench_duration_seconds","value":1735,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_programbench","value":0.005,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":2.27,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_programbench_duration_seconds","value":958,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_programbench","value":0.005,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":2.47,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_programbench_duration_seconds","value":1598,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_programbench","value":0.005,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_programbench_duration_seconds","value":4320,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_programbench","value":0.005,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":0.48,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_programbench_duration_seconds","value":1711,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_programbench","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":12.81,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_programbench_duration_seconds","value":7800,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_programbench","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":0.43,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_programbench_duration_seconds","value":4980,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_programbench","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":24.36,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_programbench_duration_seconds","value":5460,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_programbench","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":12.36,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_programbench_duration_seconds","value":21240,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_programbench","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":7.13,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_programbench_duration_seconds","value":1290,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_programbench","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_programbench_duration_seconds","value":3247,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_programbench","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":0.94,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_programbench_duration_seconds","value":2494,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_programbench","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":1.29,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_programbench_duration_seconds","value":20340,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_programbench","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":0.8,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_programbench_duration_seconds","value":19800,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_programbench","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":4.12,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_programbench_duration_seconds","value":1139,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_programbench","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_programbench_duration_seconds","value":3225,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_programbench","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":5.92,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_programbench_duration_seconds","value":2853,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_programbench","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":13.06,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_programbench_duration_seconds","value":20580,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_programbench","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_programbench_duration_seconds","value":1105,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_programbench","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_programbench_duration_seconds","value":3960,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_programbench","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":2.63,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_programbench_duration_seconds","value":756,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_programbench","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_programbench_duration_seconds","value":1981,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_programbench","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":17.99,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_programbench_duration_seconds","value":21420,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"moonshotai/kimi-k2.7-code","source":"vals-more","metric":"vals_programbench","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"moonshotai/kimi-k2.7-code","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":3.19,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"moonshotai/kimi-k2.7-code","source":"vals-more","metric":"vals_programbench_duration_seconds","value":3840,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_programbench","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_programbench_duration_seconds","value":4800,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"vals-more","metric":"vals_programbench","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"vals-more","metric":"vals_programbench_duration_seconds","value":3720,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_programbench","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_programbench_duration_seconds","value":3780,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_programbench","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":0.44,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_programbench_duration_seconds","value":419,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_programbench","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":0.34,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_programbench_duration_seconds","value":435,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_programbench","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_programbench_duration_seconds","value":457,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_programbench","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":0.36,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_programbench_duration_seconds","value":236,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"vals-more","metric":"vals_programbench","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":0.22,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"vals-more","metric":"vals_programbench_duration_seconds","value":1466,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_programbench","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":4.14,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_programbench_duration_seconds","value":2734,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_programbench","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_programbench_cost_per_test_usd","value":0.06,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_programbench_duration_seconds","value":176,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_programbench","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_programbench_duration_seconds","value":1460,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/programbench"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_srebench","value":0.5687,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_srebench_cost_per_test_usd","value":10.24,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_srebench_duration_seconds","value":1071,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_srebench","value":0.5075999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_srebench_cost_per_test_usd","value":2.69,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_srebench_duration_seconds","value":1952,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_srebench","value":0.44270000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_srebench_cost_per_test_usd","value":30.45,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_srebench_duration_seconds","value":5700,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_srebench","value":0.33590000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_srebench_cost_per_test_usd","value":34.65,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_srebench_duration_seconds","value":5820,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_srebench","value":0.3053,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_srebench_cost_per_test_usd","value":42.52,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_srebench_duration_seconds","value":5280,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_srebench","value":0.3053,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_srebench_cost_per_test_usd","value":20.65,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_srebench_duration_seconds","value":3780,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_srebench","value":0.3015,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_srebench_cost_per_test_usd","value":26.52,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_srebench_duration_seconds","value":6900,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_srebench","value":0.22899999999999998,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_srebench_cost_per_test_usd","value":32.23,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_srebench_duration_seconds","value":7380,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_srebench","value":0.12210000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_srebench_cost_per_test_usd","value":23.63,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_srebench_duration_seconds","value":4860,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_srebench","value":0.1107,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_srebench_cost_per_test_usd","value":27.46,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_srebench_duration_seconds","value":8880,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_srebench","value":0.09539999999999998,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_srebench_cost_per_test_usd","value":30.86,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_srebench_duration_seconds","value":11820,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_srebench","value":0.0916,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_srebench_cost_per_test_usd","value":27.47,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_srebench_duration_seconds","value":10080,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_srebench","value":0.0572,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_srebench_cost_per_test_usd","value":3.14,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_srebench_duration_seconds","value":3476,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_srebench","value":0.0458,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_srebench_cost_per_test_usd","value":21.47,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_srebench_duration_seconds","value":6600,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_srebench","value":0.042,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_srebench_cost_per_test_usd","value":0.4,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_srebench_duration_seconds","value":12120,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_srebench","value":0.0382,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_srebench_cost_per_test_usd","value":64.77,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_srebench_duration_seconds","value":6060,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_srebench","value":0.0382,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_srebench_cost_per_test_usd","value":17.77,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_srebench_duration_seconds","value":2788,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_srebench","value":0.0305,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_srebench_cost_per_test_usd","value":0.53,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_srebench_duration_seconds","value":8580,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_srebench","value":0.026699999999999998,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_srebench_cost_per_test_usd","value":1.55,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_srebench_duration_seconds","value":4860,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_srebench","value":0.0229,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_srebench_cost_per_test_usd","value":4.9,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_srebench_duration_seconds","value":6000,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_srebench","value":0.0191,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_srebench_cost_per_test_usd","value":5.58,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_srebench_duration_seconds","value":8400,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_srebench","value":0.015300000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_srebench_cost_per_test_usd","value":3.44,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_srebench_duration_seconds","value":6120,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_srebench","value":0.0076,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_srebench_cost_per_test_usd","value":0.55,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_srebench_duration_seconds","value":3660,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_srebench","value":0.0076,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_srebench_cost_per_test_usd","value":2.29,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_srebench_duration_seconds","value":11700,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_srebench","value":0.0076,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_srebench_cost_per_test_usd","value":13.42,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_srebench_duration_seconds","value":3960,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_srebench","value":0.0038,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_srebench_cost_per_test_usd","value":18.49,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_srebench_duration_seconds","value":13980,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_srebench","value":0.0038,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_srebench_cost_per_test_usd","value":3.07,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_srebench_duration_seconds","value":5640,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_srebench","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_srebench_cost_per_test_usd","value":26.58,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_srebench_duration_seconds","value":8940,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_srebench","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_srebench_cost_per_test_usd","value":23.43,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_srebench_duration_seconds","value":6000,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_srebench","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_srebench_cost_per_test_usd","value":11.34,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_srebench_duration_seconds","value":3780,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_srebench","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_srebench_cost_per_test_usd","value":2.23,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_srebench_duration_seconds","value":1719,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/srebench"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_ioi","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":5.31,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_ioi_duration_seconds","value":1459,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_ioi","value":1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":6.5,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_ioi_duration_seconds","value":1900,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_ioi","value":0.9689,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":1.26,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_ioi_duration_seconds","value":1891,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_ioi","value":0.9506,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":5.26,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_ioi_duration_seconds","value":1035,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_ioi","value":0.9117000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":7.98,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_ioi_duration_seconds","value":3720,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_ioi","value":0.9078,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":11.2,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_ioi_duration_seconds","value":1806,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_ioi","value":0.8761,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":8.66,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_ioi_duration_seconds","value":4980,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_ioi","value":0.8432999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":16.48,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_ioi_duration_seconds","value":3402,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_ioi","value":0.8306,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":7.52,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_ioi_duration_seconds","value":2751,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_ioi","value":0.8261,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":2.7,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_ioi_duration_seconds","value":1838,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_ioi","value":0.6889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":9.47,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_ioi_duration_seconds","value":6420,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_ioi","value":0.6844,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":7.67,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_ioi_duration_seconds","value":6360,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_ioi","value":0.6783,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":3.4,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_ioi_duration_seconds","value":1269,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_ioi","value":0.6694,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":4.54,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_ioi_duration_seconds","value":1502,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_ioi","value":0.6178,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":0.58,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_ioi_duration_seconds","value":4200,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_ioi","value":0.5932999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":1.35,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_ioi_duration_seconds","value":3660,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_ioi","value":0.5771999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":12.71,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_ioi_duration_seconds","value":2808,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_ioi","value":0.5694,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":3.98,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_ioi_duration_seconds","value":860,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_ioi","value":0.5556,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":0.2,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_ioi_duration_seconds","value":2147,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"openai/gpt-5.3-codex","source":"vals-more","metric":"vals_ioi","value":0.5383,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"openai/gpt-5.3-codex","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":2.68,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"openai/gpt-5.3-codex","source":"vals-more","metric":"vals_ioi_duration_seconds","value":1792,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_ioi","value":0.525,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":0.43,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_ioi_duration_seconds","value":5520,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_ioi","value":0.5183,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":1.25,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_ioi_duration_seconds","value":723,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_ioi","value":0.5161,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":2.15,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_ioi_duration_seconds","value":4020,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_ioi","value":0.4894,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":14.17,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_ioi_duration_seconds","value":15480,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_ioi","value":0.4767,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":0.22,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_ioi_duration_seconds","value":6540,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_ioi","value":0.47609999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":8.18,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_ioi_duration_seconds","value":14220,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_ioi","value":0.4728,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":0.83,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_ioi_duration_seconds","value":754,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_ioi","value":0.4633,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":24.46,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_ioi_duration_seconds","value":6420,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_ioi","value":0.45280000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":5.39,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_ioi_duration_seconds","value":5040,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_ioi","value":0.45,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":12.89,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_ioi_duration_seconds","value":3584,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_ioi","value":0.43939999999999996,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":2.36,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_ioi_duration_seconds","value":1791,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_ioi","value":0.4056,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":5.64,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_ioi_duration_seconds","value":5220,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_ioi","value":0.4028,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":0.24,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_ioi_duration_seconds","value":1110,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_ioi","value":0.3933,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":0.84,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_ioi_duration_seconds","value":8760,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_ioi","value":0.3906,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":3.55,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_ioi_duration_seconds","value":5940,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_ioi","value":0.38060000000000005,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":2.03,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_ioi_duration_seconds","value":4800,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_ioi","value":0.3506,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":8.67,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_ioi_duration_seconds","value":2903,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_ioi","value":0.3272,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":0.37,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_ioi_duration_seconds","value":1663,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_ioi","value":0.21780000000000002,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":2.64,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_ioi_duration_seconds","value":1535,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_ioi","value":0.1494,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":1.71,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_ioi_duration_seconds","value":1812,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_ioi","value":0.0933,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":0.34,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_ioi_duration_seconds","value":678,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_ioi","value":0.024399999999999998,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_ioi_cost_per_test_usd","value":0.16,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_ioi_duration_seconds","value":243,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/ioi"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.8764,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.5,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":383,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.8726999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":1.34,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":274,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.8576999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":1.02,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":373,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.8502,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":3.07,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":500,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.8464,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.89,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":753,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.8315,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.37,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":299,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.8315,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.63,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":466,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.8127,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":1.54,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":555,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.809,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.34,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":609,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.8051999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":1.43,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":505,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.7903,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.05,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":356,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.7828,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.45,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":643,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.7753,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":1.02,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":492,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.7753,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.47,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":520,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.764,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.74,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":427,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.764,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.02,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":810,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.7453,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.1,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":605,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.7453,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.53,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":635,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.7415999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.87,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":373,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.7378,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":1.17,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":552,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.7341,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":1.08,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":798,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.7303000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.03,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":425,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.7228,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.66,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":858,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.7191,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":2.41,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":930,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.7154,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.31,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":787,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.7079000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.58,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":410,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.6966,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.5,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":879,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.6929000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.42,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":625,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.6854,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":1.98,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":817,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.6779000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.28,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":624,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.6779000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.43,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":821,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.6779000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.07,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":939,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.6742,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.45,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":891,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.6704000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.02,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":683,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"moonshotai/kimi-k2.7-code","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.6704000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"moonshotai/kimi-k2.7-code","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.26,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"moonshotai/kimi-k2.7-code","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":784,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.6292,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.03,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":966,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.6104999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.33,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":935,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.6067,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.02,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":775,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.5843,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.68,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":893,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.5768,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":842,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.573,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.57,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":704,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.573,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.04,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":866,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.5693,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.23,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":941,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.5506,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.13,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":604,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.5506,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.14,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":1109,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.5468,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.29,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":673,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.5468,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.2,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":862,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.5393,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.15,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":376,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.5356000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.14,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":932,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.5356000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.21,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":1023,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.5318,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.2,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":778,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"qwen/qwen3.7-plus","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.5281,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"qwen/qwen3.7-plus","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.1,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"qwen/qwen3.7-plus","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":655,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.5094,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":584,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.5019,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.34,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":416,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.5019,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.07,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":594,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.5019,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.24,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":1078,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.4869,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.07,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":813,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.4757,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.63,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":772,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.442,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.41,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":306,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.4382,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.36,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":649,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.41950000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.98,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":471,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.41950000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.09,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":1051,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.4157,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.07,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":757,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.3895,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":1.19,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":989,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.3446,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.21,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":689,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.3408,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.08,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":278,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"cohere/command-a","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.17600000000000002,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"vals-more","metric":"vals_terminal_bench_2_1","value":0.10859999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"vals-more","metric":"vals_terminal_bench_2_1_cost_per_test_usd","value":0.01,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"vals-more","metric":"vals_terminal_bench_2_1_duration_seconds","value":1028,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","setting":"Terminus 2"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_swe_bench_multimodal","value":0.7021,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_swe_bench_multimodal_cost_per_test_usd","value":4.92,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_swe_bench_multimodal_duration_seconds","value":1112,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_swe_bench_multimodal","value":0.6125,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_swe_bench_multimodal_cost_per_test_usd","value":5.46,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_swe_bench_multimodal_duration_seconds","value":912,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_swe_bench_multimodal","value":0.5832999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_swe_bench_multimodal_cost_per_test_usd","value":4.53,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_swe_bench_multimodal_duration_seconds","value":1453,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_swe_bench_multimodal","value":0.5604,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_swe_bench_multimodal_cost_per_test_usd","value":11.4,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_swe_bench_multimodal_duration_seconds","value":2018,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_swe_bench_multimodal","value":0.4646,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_swe_bench_multimodal_cost_per_test_usd","value":0.23,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_swe_bench_multimodal_duration_seconds","value":1164,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_swe_bench_multimodal","value":0.45630000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_swe_bench_multimodal_cost_per_test_usd","value":1.7,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_swe_bench_multimodal_duration_seconds","value":584,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_swe_bench_multimodal","value":0.44170000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_swe_bench_multimodal_cost_per_test_usd","value":1.65,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_swe_bench_multimodal_duration_seconds","value":1365,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_swe_bench_multimodal","value":0.4396,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_swe_bench_multimodal_cost_per_test_usd","value":0.7,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_swe_bench_multimodal_duration_seconds","value":976,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_swe_bench_multimodal","value":0.4354,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_swe_bench_multimodal_cost_per_test_usd","value":0.35,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_swe_bench_multimodal_duration_seconds","value":416,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_swe_bench_multimodal","value":0.43329999999999996,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_swe_bench_multimodal_cost_per_test_usd","value":1.81,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_swe_bench_multimodal_duration_seconds","value":423,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_swe_bench_multimodal","value":0.4292,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_swe_bench_multimodal_cost_per_test_usd","value":4.66,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_swe_bench_multimodal_duration_seconds","value":1261,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_swe_bench_multimodal","value":0.425,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_swe_bench_multimodal_cost_per_test_usd","value":0.99,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_swe_bench_multimodal_duration_seconds","value":1124,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_swe_bench_multimodal","value":0.4125,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_swe_bench_multimodal_cost_per_test_usd","value":0.12,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_swe_bench_multimodal_duration_seconds","value":2763,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_swe_bench_multimodal","value":0.4083,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_swe_bench_multimodal_cost_per_test_usd","value":3.69,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_swe_bench_multimodal_duration_seconds","value":1338,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_swe_bench_multimodal","value":0.4083,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_swe_bench_multimodal_cost_per_test_usd","value":0.61,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_swe_bench_multimodal_duration_seconds","value":1566,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_swe_bench_multimodal","value":0.375,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_swe_bench_multimodal_cost_per_test_usd","value":0.03,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_swe_bench_multimodal_duration_seconds","value":316,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_swe_bench_multimodal","value":0.3333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_swe_bench_multimodal_cost_per_test_usd","value":1.02,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_swe_bench_multimodal_duration_seconds","value":789,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_swe_bench_multimodal","value":0.33130000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_swe_bench_multimodal_cost_per_test_usd","value":5.14,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_swe_bench_multimodal_duration_seconds","value":1647,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/swebench-multimodal"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_vibe_code_1_100","value":0.3036,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_vibe_code_1_100_cost_per_test_usd","value":44.12,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_vibe_code_1_100_duration_seconds","value":8880,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_vibe_code_1_100","value":0.2853,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_vibe_code_1_100_cost_per_test_usd","value":41.49,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_vibe_code_1_100_duration_seconds","value":4920,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_vibe_code_1_100","value":0.28,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_vibe_code_1_100_cost_per_test_usd","value":149.66,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_vibe_code_1_100_duration_seconds","value":10380,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_vibe_code_1_100","value":0.2764,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_vibe_code_1_100_cost_per_test_usd","value":84.72,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_vibe_code_1_100_duration_seconds","value":12360,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_vibe_code_1_100","value":0.2655,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_vibe_code_1_100_cost_per_test_usd","value":13.72,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_vibe_code_1_100_duration_seconds","value":1868,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_vibe_code_1_100","value":0.2259,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_vibe_code_1_100_cost_per_test_usd","value":4.91,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_vibe_code_1_100_duration_seconds","value":7380,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_vibe_code_1_100","value":0.212,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_vibe_code_1_100_cost_per_test_usd","value":18.66,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_vibe_code_1_100_duration_seconds","value":6180,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_vibe_code_1_100","value":0.2041,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_vibe_code_1_100_cost_per_test_usd","value":8.3,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_vibe_code_1_100_duration_seconds","value":14760,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_vibe_code_1_100","value":0.20010000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_vibe_code_1_100_cost_per_test_usd","value":47.43,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_vibe_code_1_100_duration_seconds","value":9420,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_vibe_code_1_100","value":0.1999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_vibe_code_1_100_cost_per_test_usd","value":8.24,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_vibe_code_1_100_duration_seconds","value":5160,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_vibe_code_1_100","value":0.1877,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_vibe_code_1_100_cost_per_test_usd","value":18.91,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_vibe_code_1_100_duration_seconds","value":3960,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_vibe_code_1_100","value":0.18239999999999998,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_vibe_code_1_100_cost_per_test_usd","value":9.4,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_vibe_code_1_100_duration_seconds","value":6480,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_vibe_code_1_100","value":0.1753,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_vibe_code_1_100_cost_per_test_usd","value":5.89,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_vibe_code_1_100_duration_seconds","value":2262,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_vibe_code_1_100","value":0.1638,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_vibe_code_1_100_cost_per_test_usd","value":0.69,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_vibe_code_1_100_duration_seconds","value":1701,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_vibe_code_1_100","value":0.1603,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_vibe_code_1_100_cost_per_test_usd","value":0.46,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_vibe_code_1_100_duration_seconds","value":2343,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_vibe_code_1_100","value":0.1482,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_vibe_code_1_100_cost_per_test_usd","value":33.33,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_vibe_code_1_100_duration_seconds","value":6540,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_vibe_code_1_100","value":0.1475,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_vibe_code_1_100_cost_per_test_usd","value":26.27,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_vibe_code_1_100_duration_seconds","value":7860,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_vibe_code_1_100","value":0.1426,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_vibe_code_1_100_cost_per_test_usd","value":6.75,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_vibe_code_1_100_duration_seconds","value":3593,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_vibe_code_1_100","value":0.1382,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_vibe_code_1_100_cost_per_test_usd","value":71.15,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_vibe_code_1_100_duration_seconds","value":15360,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_vibe_code_1_100","value":0.1283,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_vibe_code_1_100_cost_per_test_usd","value":9.68,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_vibe_code_1_100_duration_seconds","value":5760,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_vibe_code_1_100","value":0.0922,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_vibe_code_1_100_cost_per_test_usd","value":3.03,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_vibe_code_1_100_duration_seconds","value":1570,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_vibe_code_1_100","value":0.0733,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_vibe_code_1_100_cost_per_test_usd","value":5,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_vibe_code_1_100_duration_seconds","value":3002,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_vibe_code_1_100","value":0.0669,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_vibe_code_1_100_cost_per_test_usd","value":3.36,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_vibe_code_1_100_duration_seconds","value":688,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vcb-1-100"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_skillsbench","value":0.698,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_skillsbench_cost_per_test_usd","value":0.09,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_skillsbench_duration_seconds","value":223,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_skillsbench","value":0.6603,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_skillsbench_cost_per_test_usd","value":0.58,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_skillsbench_duration_seconds","value":136,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_skillsbench","value":0.6589,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_skillsbench_cost_per_test_usd","value":1.8,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_skillsbench_duration_seconds","value":186,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_skillsbench","value":0.6255,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"Codex"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_skillsbench_cost_per_test_usd","value":1.57,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"Codex"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_skillsbench_duration_seconds","value":280,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"Codex"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_skillsbench","value":0.6154999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_skillsbench_cost_per_test_usd","value":4.52,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_skillsbench_duration_seconds","value":662,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_skillsbench","value":0.6045,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_skillsbench_cost_per_test_usd","value":0.21,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_skillsbench_duration_seconds","value":320,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_skillsbench","value":0.6043999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_skillsbench_cost_per_test_usd","value":2.51,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_skillsbench_duration_seconds","value":505,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_skillsbench","value":0.5922999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_skillsbench_cost_per_test_usd","value":4.77,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_skillsbench_duration_seconds","value":930,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_skillsbench","value":0.5919,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_skillsbench_cost_per_test_usd","value":0.45,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_skillsbench_duration_seconds","value":376,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_skillsbench","value":0.589,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_skillsbench_cost_per_test_usd","value":1.75,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_skillsbench_duration_seconds","value":415,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_skillsbench","value":0.5798,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_skillsbench_cost_per_test_usd","value":2.34,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_skillsbench_duration_seconds","value":235,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_skillsbench","value":0.5577000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_skillsbench_cost_per_test_usd","value":0.92,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_skillsbench_duration_seconds","value":808,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"qwen/qwen3.7-plus","source":"vals-more","metric":"vals_skillsbench","value":0.5429999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"qwen/qwen3.7-plus","source":"vals-more","metric":"vals_skillsbench_cost_per_test_usd","value":0.14,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"qwen/qwen3.7-plus","source":"vals-more","metric":"vals_skillsbench_duration_seconds","value":724,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_skillsbench","value":0.541,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_skillsbench_cost_per_test_usd","value":4.14,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_skillsbench_duration_seconds","value":787,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_skillsbench","value":0.5383,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_skillsbench_cost_per_test_usd","value":0.37,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_skillsbench_duration_seconds","value":675,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_skillsbench","value":0.5304,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_skillsbench_cost_per_test_usd","value":0.65,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_skillsbench_duration_seconds","value":780,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_skillsbench","value":0.5274,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_skillsbench_cost_per_test_usd","value":1.25,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_skillsbench_duration_seconds","value":435,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_skillsbench","value":0.5171,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_skillsbench_cost_per_test_usd","value":2.04,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_skillsbench_duration_seconds","value":542,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_skillsbench","value":0.515,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_skillsbench_cost_per_test_usd","value":0.5,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_skillsbench_duration_seconds","value":928,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_skillsbench","value":0.5127,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_skillsbench_cost_per_test_usd","value":0.4,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_skillsbench_duration_seconds","value":496,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_skillsbench","value":0.5067,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_skillsbench_cost_per_test_usd","value":0.13,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_skillsbench_duration_seconds","value":412,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"moonshotai/kimi-k2.7-code","source":"vals-more","metric":"vals_skillsbench","value":0.5004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"moonshotai/kimi-k2.7-code","source":"vals-more","metric":"vals_skillsbench_cost_per_test_usd","value":0.44,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"moonshotai/kimi-k2.7-code","source":"vals-more","metric":"vals_skillsbench_duration_seconds","value":804,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_skillsbench","value":0.4905,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_skillsbench_cost_per_test_usd","value":1.38,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_skillsbench_duration_seconds","value":860,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_skillsbench","value":0.47509999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_skillsbench_cost_per_test_usd","value":0.71,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_skillsbench_duration_seconds","value":787,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_skillsbench","value":0.4648,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_skillsbench_cost_per_test_usd","value":2.9,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_skillsbench_duration_seconds","value":912,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_skillsbench","value":0.4508,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_skillsbench_cost_per_test_usd","value":0.81,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_skillsbench_duration_seconds","value":1192,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_skillsbench","value":0.4201,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_skillsbench_cost_per_test_usd","value":0.52,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_skillsbench_duration_seconds","value":948,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_skillsbench","value":0.4064,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_skillsbench_cost_per_test_usd","value":0.42,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_skillsbench_duration_seconds","value":277,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_skillsbench","value":0.40159999999999996,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_skillsbench_cost_per_test_usd","value":0.04,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_skillsbench_duration_seconds","value":729,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_skillsbench","value":0.3811,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_skillsbench_cost_per_test_usd","value":0.82,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_skillsbench_duration_seconds","value":401,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_skillsbench","value":0.3358,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_skillsbench_cost_per_test_usd","value":0.15,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_skillsbench_duration_seconds","value":701,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_skillsbench","value":0.27949999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_skillsbench_cost_per_test_usd","value":0.06,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_skillsbench_duration_seconds","value":292,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_skillsbench","value":0.2609,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_skillsbench_cost_per_test_usd","value":0.83,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_skillsbench_duration_seconds","value":939,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_skillsbench","value":0.18059999999999998,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_skillsbench_cost_per_test_usd","value":0.1,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_skillsbench_duration_seconds","value":49.36,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/skillsbench","setting":"OpenHands"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_cyberbench","value":0.8036,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":3.66,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":825,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_cyberbench","value":0.7798,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":1.34,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":734,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_cyberbench","value":0.7786,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":5.11,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":1150,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_cyberbench","value":0.7631,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":3.05,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":647,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_cyberbench","value":0.7625,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":0.13,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":950,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_cyberbench","value":0.7548,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":1.25,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":1959,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_cyberbench","value":0.7536,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":0.05,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":1702,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_cyberbench","value":0.7524,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":2.13,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":1844,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_cyberbench","value":0.7458,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":4.17,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":1382,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_cyberbench","value":0.7369,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":0.07,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":830,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_cyberbench","value":0.7363,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":0.4,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":975,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_cyberbench","value":0.7286,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":0.59,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":1353,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_cyberbench","value":0.7286,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":0.09,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":1661,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_cyberbench","value":0.7208,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":0.19,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":928,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_cyberbench","value":0.7208,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":3.31,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":1024,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_cyberbench","value":0.7208,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":2.69,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":1818,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_cyberbench","value":0.7101000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":2.95,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":848,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_cyberbench","value":0.7042,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":4.01,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":1112,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_cyberbench","value":0.703,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":4.84,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":1377,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_cyberbench","value":0.6951999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":2.15,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":1221,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_cyberbench","value":0.6951999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":2.43,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":1322,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_cyberbench","value":0.6945999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":8.54,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":930,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_cyberbench","value":0.6940999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":4.26,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":1493,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_cyberbench","value":0.6786,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":0.14,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":2148,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_cyberbench","value":0.6779999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":0.99,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":2496,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_cyberbench","value":0.6768000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":4.07,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":2212,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_cyberbench","value":0.6679,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":1.46,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":811,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_cyberbench","value":0.6536,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":2.87,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":1165,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_cyberbench","value":0.6536,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":0.49,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":2203,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_cyberbench","value":0.65,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":3.41,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":2456,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_cyberbench","value":0.6411,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":0.25,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":1175,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_cyberbench","value":0.5958,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":4.42,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":2033,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_cyberbench","value":0.5911,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":0.43,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":1076,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_cyberbench","value":0.4548,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":0.12,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":1139,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_cyberbench","value":0.4536,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":1.31,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":660,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_cyberbench","value":0.4375,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":2.15,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":454,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_cyberbench","value":0.4375,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":1.31,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":589,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_cyberbench","value":0.4107,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":1.84,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":250,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_cyberbench","value":0.39289999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":0.29,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":222,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"vals-more","metric":"vals_cyberbench","value":0.29460000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":0.09,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":3032,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_cyberbench","value":0.2857,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_cyberbench_cost_per_test_usd","value":0.78,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_cyberbench_duration_seconds","value":580,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cyber"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_finance_agent","value":0.654,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":4.38,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":981,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_finance_agent","value":0.6144,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":2,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":201,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"meta/muse-spark-open","source":"vals-more","metric":"vals_finance_agent","value":0.6134000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"meta/muse-spark-open","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.77,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"meta/muse-spark-open","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":1453,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_finance_agent","value":0.606,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.77,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":304,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_finance_agent","value":0.5904,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":1.48,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":181,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_finance_agent","value":0.589,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.74,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":342,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_finance_agent","value":0.5888,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":8.35,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":1094,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_finance_agent","value":0.5863,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":5.12,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":598,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_finance_agent","value":0.5859000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":9.22,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":1988,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_finance_agent","value":0.581,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":6.55,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":1903,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_finance_agent","value":0.5786,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":2.51,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":322,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_finance_agent","value":0.5785,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.05,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":891,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_finance_agent","value":0.5734,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.2,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":648,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_finance_agent","value":0.5721,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.72,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":415,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"vals-more","metric":"vals_finance_agent","value":0.5696,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.46,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":879,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_finance_agent","value":0.5664,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":2.67,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":369,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_finance_agent","value":0.5631,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":8.06,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":611,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_finance_agent","value":0.563,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":1.4,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":225,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_finance_agent","value":0.5628,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.07,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":422,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_finance_agent","value":0.5584,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":1.07,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":950,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_finance_agent","value":0.5506,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.59,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":1425,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_finance_agent","value":0.5504,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.28,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":772,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_finance_agent","value":0.5468,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":1.2,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":1562,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_finance_agent","value":0.5444,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":3.63,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":1450,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_finance_agent","value":0.5414,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":1.64,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":1849,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_finance_agent","value":0.5392,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":4.22,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":547,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_finance_agent","value":0.5390999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.75,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":792,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_finance_agent","value":0.5376,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":1.25,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":1165,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_finance_agent","value":0.5367999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":1.66,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":1001,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_finance_agent","value":0.5354,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":6.82,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":693,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_finance_agent","value":0.5347999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.21,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":364,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_finance_agent","value":0.5311,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":1.91,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":286,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_finance_agent","value":0.5225,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":2.72,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":933,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_finance_agent","value":0.5203,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":1.62,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":925,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_finance_agent","value":0.5185,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":1.95,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":799,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_finance_agent","value":0.5176,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":4.15,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":662,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_finance_agent","value":0.5151,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":4.03,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":360,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_finance_agent","value":0.5103,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":2.41,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":696,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_finance_agent","value":0.5067,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.62,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":748,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_finance_agent","value":0.5059,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":1.24,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":1175,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_finance_agent","value":0.5039,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.88,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":975,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_finance_agent","value":0.4987,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.12,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":898,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_finance_agent","value":0.49700000000000005,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.71,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":473,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_finance_agent","value":0.49520000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.28,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":490,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_finance_agent","value":0.4905,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":2.12,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":540,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_finance_agent","value":0.4855,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.75,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":622,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_finance_agent","value":0.48350000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":1.16,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":289,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_finance_agent","value":0.4827,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.32,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":497,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_finance_agent","value":0.4778,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.55,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":635,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_finance_agent","value":0.4744,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.39,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":143,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_finance_agent","value":0.466,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":1,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":1082,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_finance_agent","value":0.4536,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":1.2,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":2154,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_finance_agent","value":0.449,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":1.14,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":1630,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_finance_agent","value":0.44789999999999996,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.62,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":924,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_finance_agent","value":0.44079999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.88,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":1526,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_finance_agent","value":0.42979999999999996,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":1.59,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":208,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_finance_agent","value":0.4255,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.57,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":247,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_finance_agent","value":0.415,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.21,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":497,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_finance_agent","value":0.41259999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.23,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":994,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_finance_agent","value":0.40850000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.81,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":612,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"qwen/qwen3.7-plus","source":"vals-more","metric":"vals_finance_agent","value":0.3822,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"qwen/qwen3.7-plus","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.36,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"qwen/qwen3.7-plus","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":542,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_finance_agent","value":0.3822,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.16,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":335,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_finance_agent","value":0.37729999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.85,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":615,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"vals-more","metric":"vals_finance_agent","value":0.37670000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":254,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_finance_agent","value":0.36729999999999996,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.09,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":339,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_finance_agent","value":0.3579,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.29,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":752,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_finance_agent","value":0.321,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":1.91,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":768,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_finance_agent","value":0.31010000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.6,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":177,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_finance_agent","value":0.3031,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.05,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":157,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_finance_agent","value":0.2999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.14,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":54.78,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_finance_agent","value":0.2849,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.79,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":351,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_finance_agent","value":0.2789,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.18,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":804,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_finance_agent","value":0.1889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.11,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":92.48,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"vals-more","metric":"vals_finance_agent","value":0.185,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"vals-more","metric":"vals_finance_agent_cost_per_test_usd","value":0.03,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":540,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"cohere/command-a","source":"vals-more","metric":"vals_finance_agent","value":0.0904,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"cohere/command-a","source":"vals-more","metric":"vals_finance_agent_duration_seconds","value":567,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/fabv2"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_tax_agent","value":0.4919,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":13.18,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":1714,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_tax_agent","value":0.4557,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":15.09,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":4020,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_tax_agent","value":0.45549999999999996,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":5.14,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":1008,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_tax_agent","value":0.4456,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":3.47,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":986,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"vals-more","metric":"vals_tax_agent","value":0.4435,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.46,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":1264,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_tax_agent","value":0.41960000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":9.25,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":3561,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_tax_agent","value":0.397,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":1.8,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":3053,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_tax_agent","value":0.38280000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":6.7,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":867,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_tax_agent","value":0.3627,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":1.88,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":493,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_tax_agent","value":0.35969999999999996,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.32,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":505,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_tax_agent","value":0.342,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":1.8,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":996,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_tax_agent","value":0.3337,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":2.79,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":2415,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_tax_agent","value":0.33140000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.98,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":658,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_tax_agent","value":0.32799999999999996,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.27,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":119.91,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_tax_agent","value":0.3262,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.59,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":2464,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_tax_agent","value":0.3239,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.13,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":1548,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_tax_agent","value":0.3212,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.86,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":178,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_tax_agent","value":0.3209,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":1.55,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":2436,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_tax_agent","value":0.31920000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":1.16,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":2974,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_tax_agent","value":0.3155,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.14,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":1297,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_tax_agent","value":0.3109,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":7.51,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":2681,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_tax_agent","value":0.31079999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":2.97,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":1846,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_tax_agent","value":0.3089,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.82,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":1334,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_tax_agent","value":0.3039,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":2.72,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":3438,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_tax_agent","value":0.3004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":4.83,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":3660,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_tax_agent","value":0.3,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":1.69,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":479,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_tax_agent","value":0.2937,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":1.79,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":1159,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_tax_agent","value":0.2851,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.05,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":1039,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_tax_agent","value":0.2807,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.16,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":337,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_tax_agent","value":0.2727,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.55,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":1289,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_tax_agent","value":0.2676,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.73,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":1597,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_tax_agent","value":0.2663,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.13,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":349,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"meta/muse-spark-open","source":"vals-more","metric":"vals_tax_agent","value":0.2632,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"meta/muse-spark-open","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.88,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"meta/muse-spark-open","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":702,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_tax_agent","value":0.2584,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":1.19,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":707,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_tax_agent","value":0.25170000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.72,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":1245,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_tax_agent","value":0.2486,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.47,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":284,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_tax_agent","value":0.2482,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.47,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":2566,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_tax_agent","value":0.23739999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":1.27,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":279,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_tax_agent","value":0.228,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.48,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":87.24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_tax_agent","value":0.21760000000000002,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":4.07,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":952,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_tax_agent","value":0.2175,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":1.32,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":1214,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_tax_agent","value":0.2165,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.86,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":233,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_tax_agent","value":0.2072,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":5.8,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":901,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_tax_agent","value":0.2059,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.16,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":315,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_tax_agent","value":0.19949999999999998,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.19,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":1996,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_tax_agent","value":0.1804,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.36,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":105.32,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_tax_agent","value":0.1583,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.44,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":210,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_tax_agent","value":0.1539,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.09,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":385,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_tax_agent","value":0.15289999999999998,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.35,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":811,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_tax_agent","value":0.15,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":2.28,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":1052,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_tax_agent","value":0.124,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.57,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":924,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_tax_agent","value":0.1184,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.1,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":100.62,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_tax_agent","value":0.115,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.04,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":377,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"qwen/qwen3.7-plus","source":"vals-more","metric":"vals_tax_agent","value":0.1047,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"qwen/qwen3.7-plus","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.09,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"qwen/qwen3.7-plus","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":310,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_tax_agent","value":0.0929,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.3,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":100.96,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_tax_agent","value":0.08810000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.81,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":1006,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_tax_agent","value":0.07769999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.02,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":501,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_tax_agent","value":0.0768,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.3,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":378,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_tax_agent","value":0.0725,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.08,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":47.46,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_tax_agent","value":0.0695,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.12,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":89.26,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_tax_agent","value":0.0687,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.12,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":303,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_tax_agent","value":0.061799999999999994,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.12,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":97.52,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_tax_agent","value":0.058600000000000006,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.23,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":155,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_tax_agent","value":0.049699999999999994,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.07,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":220,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_tax_agent","value":0.044800000000000006,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":1.44,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":431,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_tax_agent","value":0.0311,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.01,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":18.74,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"vals-more","metric":"vals_tax_agent","value":0.0259,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.03,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":1180,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_tax_agent","value":0.024900000000000002,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_tax_agent_cost_per_test_usd","value":0.02,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_tax_agent_duration_seconds","value":29.67,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_agent_bench"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_legal_research","value":0.5529,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":6.76,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":1861,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_legal_research","value":0.5529,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":23.06,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":3449,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_legal_research","value":0.5481,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":6.45,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":1881,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_legal_research","value":0.5047999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":3.98,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":927,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_legal_research","value":0.5047999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":25.16,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":6720,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_legal_research","value":0.49520000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":9.79,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":1338,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_legal_research","value":0.4904,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":2.24,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":3110,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_legal_research","value":0.4808,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":1.53,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":1504,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_legal_research","value":0.4808,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":21.61,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":4620,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_legal_research","value":0.4808,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":14.83,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":5580,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_legal_research","value":0.47600000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":2.49,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":3660,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_legal_research","value":0.47119999999999995,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":4.92,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":1274,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_legal_research","value":0.47119999999999995,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.18,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":1816,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_legal_research","value":0.46149999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":3.47,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":760,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"vals-more","metric":"vals_legal_research","value":0.45189999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.7,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":2107,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_legal_research","value":0.45189999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.12,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":3067,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_legal_research","value":0.45189999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.85,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":3840,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_legal_research","value":0.4471,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":3.67,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":2314,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_legal_research","value":0.4375,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.51,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":307,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_legal_research","value":0.4375,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":2.82,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":714,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_legal_research","value":0.43270000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":1.63,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":4920,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_legal_research","value":0.4183,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":2.72,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":1546,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_legal_research","value":0.41350000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.25,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":702,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_legal_research","value":0.41350000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":7.91,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":4200,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_legal_research","value":0.40869999999999995,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.65,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":531,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_legal_research","value":0.40869999999999995,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":1.09,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":2527,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_legal_research","value":0.40380000000000005,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.84,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":2168,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_legal_research","value":0.40380000000000005,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":7.4,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":2265,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_legal_research","value":0.3942,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":10.58,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":1491,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_legal_research","value":0.38939999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":1.63,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":324,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_legal_research","value":0.3846,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":3.06,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":512,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_legal_research","value":0.3846,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":2.3,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":990,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"meta/muse-spark-open","source":"vals-more","metric":"vals_legal_research","value":0.3846,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"meta/muse-spark-open","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":1.56,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"meta/muse-spark-open","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":1763,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_legal_research","value":0.3846,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":3.38,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":2060,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_legal_research","value":0.37979999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.38,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":313,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_legal_research","value":0.37979999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.07,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":920,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_legal_research","value":0.37979999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":1.09,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":954,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_legal_research","value":0.3654,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.85,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":2374,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_legal_research","value":0.36060000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":2.16,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":1601,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_legal_research","value":0.34619999999999995,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.76,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":289,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_legal_research","value":0.3173,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":5.33,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":5580,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_legal_research","value":0.3125,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.89,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":1023,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_legal_research","value":0.3077,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":1.31,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":278,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_legal_research","value":0.3029,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.28,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":1267,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_legal_research","value":0.3029,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.44,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":2548,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_legal_research","value":0.2981,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.34,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":814,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_legal_research","value":0.28850000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":4.9,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":1449,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_legal_research","value":0.2836,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.49,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":869,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_legal_research","value":0.2789,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.39,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":326,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_legal_research","value":0.2548,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.14,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":775,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_legal_research","value":0.2548,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":1.4,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":809,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_legal_research","value":0.25,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.47,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":168,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_legal_research","value":0.23079999999999998,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.68,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":1025,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_legal_research","value":0.20670000000000002,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":1.1,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":242,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_legal_research","value":0.1827,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.14,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":188,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"qwen/qwen3.7-plus","source":"vals-more","metric":"vals_legal_research","value":0.1635,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"qwen/qwen3.7-plus","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.3,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"qwen/qwen3.7-plus","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":832,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_legal_research","value":0.15869999999999998,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.08,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":416,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_legal_research","value":0.15869999999999998,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.23,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":1333,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_legal_research","value":0.15869999999999998,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":1.52,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":1853,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_legal_research","value":0.15380000000000002,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.2,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":84.58,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"vals-more","metric":"vals_legal_research","value":0.15380000000000002,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":611,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_legal_research","value":0.149,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.7,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":659,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_legal_research","value":0.1394,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.12,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":59.2,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_legal_research","value":0.1394,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.26,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":244,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_legal_research","value":0.125,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":1.86,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":2256,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_legal_research","value":0.1058,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.27,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":243,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_legal_research","value":0.1058,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.22,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":421,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_legal_research","value":0.0913,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.03,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":391,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_legal_research","value":0.0913,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":1.31,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":613,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_legal_research","value":0.0625,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.14,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":527,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_legal_research","value":0.0433,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.06,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":47.61,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_legal_research","value":0.0337,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.01,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":20.4,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"vals-more","metric":"vals_legal_research","value":0.0288,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":285,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_legal_research","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_legal_research_cost_per_test_usd","value":0.04,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_legal_research_duration_seconds","value":212,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_research"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_harvey_legal_agent","value":0.2708,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_harvey_legal_agent_cost_per_test_usd","value":10.55,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_harvey_legal_agent_duration_seconds","value":1755,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_harvey_legal_agent","value":0.2375,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_harvey_legal_agent_cost_per_test_usd","value":7.08,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_harvey_legal_agent_duration_seconds","value":906,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_harvey_legal_agent","value":0.1833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_harvey_legal_agent_cost_per_test_usd","value":10.75,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_harvey_legal_agent_duration_seconds","value":2148,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_harvey_legal_agent","value":0.175,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_harvey_legal_agent_cost_per_test_usd","value":4.18,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_harvey_legal_agent_duration_seconds","value":3484,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_harvey_legal_agent","value":0.1458,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_harvey_legal_agent_cost_per_test_usd","value":3.99,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_harvey_legal_agent_duration_seconds","value":1911,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"vals-more","metric":"vals_harvey_legal_agent","value":0.1417,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"vals-more","metric":"vals_harvey_legal_agent_cost_per_test_usd","value":0.61,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"vals-more","metric":"vals_harvey_legal_agent_duration_seconds","value":1328,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_harvey_legal_agent","value":0.1375,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_harvey_legal_agent_cost_per_test_usd","value":0.22,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_harvey_legal_agent_duration_seconds","value":1862,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_harvey_legal_agent","value":0.1333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_harvey_legal_agent_cost_per_test_usd","value":0.09,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_harvey_legal_agent_duration_seconds","value":1343,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_harvey_legal_agent","value":0.1292,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_harvey_legal_agent_cost_per_test_usd","value":4.14,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_harvey_legal_agent_duration_seconds","value":2556,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_harvey_legal_agent","value":0.1208,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_harvey_legal_agent_cost_per_test_usd","value":3.66,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_harvey_legal_agent_duration_seconds","value":1162,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_harvey_legal_agent","value":0.10830000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_harvey_legal_agent_cost_per_test_usd","value":0.8,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_harvey_legal_agent_duration_seconds","value":655,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_harvey_legal_agent","value":0.1042,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_harvey_legal_agent_cost_per_test_usd","value":0.32,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_harvey_legal_agent_duration_seconds","value":745,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_harvey_legal_agent","value":0.1042,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_harvey_legal_agent_cost_per_test_usd","value":16.61,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_harvey_legal_agent_duration_seconds","value":4380,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_harvey_legal_agent","value":0.0917,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_harvey_legal_agent_cost_per_test_usd","value":21.38,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_harvey_legal_agent_duration_seconds","value":3507,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_harvey_legal_agent","value":0.0875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_harvey_legal_agent_cost_per_test_usd","value":0.98,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_harvey_legal_agent_duration_seconds","value":1989,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_harvey_legal_agent","value":0.0708,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_harvey_legal_agent_cost_per_test_usd","value":25.46,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_harvey_legal_agent_duration_seconds","value":1953,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_harvey_legal_agent","value":0.0625,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_harvey_legal_agent_cost_per_test_usd","value":3.54,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_harvey_legal_agent_duration_seconds","value":2426,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_harvey_legal_agent","value":0.0417,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_harvey_legal_agent_cost_per_test_usd","value":0.3,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_harvey_legal_agent_duration_seconds","value":1305,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_harvey_legal_agent","value":0.0417,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_harvey_legal_agent_cost_per_test_usd","value":4.26,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_harvey_legal_agent_duration_seconds","value":2621,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_harvey_legal_agent","value":0.0375,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_harvey_legal_agent_cost_per_test_usd","value":1.25,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_harvey_legal_agent_duration_seconds","value":530,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_harvey_legal_agent","value":0.0292,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_harvey_legal_agent_cost_per_test_usd","value":0.18,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_harvey_legal_agent_duration_seconds","value":455,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/hlab"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_excel_modeling","value":0.7667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":15.93,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":1772,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_excel_modeling","value":0.7594,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":11.02,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":2106,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_excel_modeling","value":0.7570999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":8.79,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":2205,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_excel_modeling","value":0.7524,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":11.8,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":2306,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_excel_modeling","value":0.7367,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":12.35,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":1594,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_excel_modeling","value":0.7356,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":6.07,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":1559,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_excel_modeling","value":0.7234,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":6.01,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":590,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_excel_modeling","value":0.722,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":8.24,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":769,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_excel_modeling","value":0.7170000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":5.83,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":804,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_excel_modeling","value":0.7153,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":1.28,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":622,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_excel_modeling","value":0.7132999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":5.69,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":651,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_excel_modeling","value":0.7077,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":1.14,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":1108,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_excel_modeling","value":0.6937000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":12.06,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":2632,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_excel_modeling","value":0.6851999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":0.14,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":1041,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_excel_modeling","value":0.6712,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":0.37,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":660,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_excel_modeling","value":0.6708,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":5.6,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":1034,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_excel_modeling","value":0.6698999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":6.48,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":2097,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_excel_modeling","value":0.6668000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":3.07,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":741,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_excel_modeling","value":0.6631999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":10.29,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":2986,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_excel_modeling","value":0.662,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":2.19,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":813,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_excel_modeling","value":0.6546,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":0.11,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":1522,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_excel_modeling","value":0.6541,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":3.89,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":726,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_excel_modeling","value":0.6454000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":3.27,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":911,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_excel_modeling","value":0.6373,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":12.76,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":2316,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_excel_modeling","value":0.6355,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":5.17,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":1124,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_excel_modeling","value":0.6336999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":2.46,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":1867,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_excel_modeling","value":0.6286,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":0.33,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":3314,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_excel_modeling","value":0.6273,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":3.06,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":3179,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_excel_modeling","value":0.6271,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":3.55,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":1375,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"vals-more","metric":"vals_excel_modeling","value":0.618,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":0.36,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":1007,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_excel_modeling","value":0.6153,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":4.47,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":3532,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_excel_modeling","value":0.6015,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":7.23,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":3256,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_excel_modeling","value":0.6007,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":2.66,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":3467,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_excel_modeling","value":0.5966,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":4.56,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":1371,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_excel_modeling","value":0.5902000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":1.15,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":1083,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_excel_modeling","value":0.5808,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":0.79,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":1839,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_excel_modeling","value":0.5785,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":2.2,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":2388,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_excel_modeling","value":0.5721,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":0.23,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":780,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_excel_modeling","value":0.5711999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":1.33,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":2615,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_excel_modeling","value":0.5704,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":2.86,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":1957,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_excel_modeling","value":0.5698,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":2.31,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":1027,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_excel_modeling","value":0.5698,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":0.38,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":1574,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_excel_modeling","value":0.5636,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":1.11,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":892,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_excel_modeling","value":0.5634,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":3.79,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":2172,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_excel_modeling","value":0.5621,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":4.84,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":4920,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_excel_modeling","value":0.5593,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":0.71,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":4500,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_excel_modeling","value":0.5523,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":0.22,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":1748,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_excel_modeling","value":0.5509000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":0.08,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":1838,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"meta/muse-spark-open","source":"vals-more","metric":"vals_excel_modeling","value":0.5367000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"meta/muse-spark-open","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":5.35,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"meta/muse-spark-open","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":5100,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_excel_modeling","value":0.5291,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":1.55,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":1108,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_excel_modeling","value":0.528,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":1.08,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":2247,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_excel_modeling","value":0.5262,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":3.77,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":709,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_excel_modeling","value":0.5162,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":0.8,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":822,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"qwen/qwen3.7-plus","source":"vals-more","metric":"vals_excel_modeling","value":0.49340000000000006,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"qwen/qwen3.7-plus","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":0.6,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"qwen/qwen3.7-plus","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":2209,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_excel_modeling","value":0.47759999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":2.09,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":1890,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_excel_modeling","value":0.4543,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":2.15,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":2601,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_excel_modeling","value":0.4475,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":0.57,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":1767,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_excel_modeling","value":0.43229999999999996,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":1.23,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":494,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_excel_modeling","value":0.3836,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":1.67,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":1582,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_excel_modeling","value":0.3287,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":2.87,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":1874,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_excel_modeling","value":0.3176,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":0.25,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":1174,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"vals-more","metric":"vals_excel_modeling","value":0.3173,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":2382,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_excel_modeling","value":0.2847,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":0.79,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":3780,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_excel_modeling","value":0.2845,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":1.66,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":1207,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_excel_modeling","value":0.2602,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":0.45,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":329,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_excel_modeling","value":0.2501,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":0.18,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":735,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_excel_modeling","value":0.2266,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":1.03,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":719,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_excel_modeling","value":0.1839,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":0.63,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":272,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"vals-more","metric":"vals_excel_modeling","value":0.1699,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":0.18,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":2359,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_excel_modeling","value":0.1174,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":0.47,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":368,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_excel_modeling","value":0.1119,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":10.6,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":3082,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_excel_modeling","value":0.08789999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":0.42,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":301,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_excel_modeling","value":0.0863,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_excel_modeling_cost_per_test_usd","value":0.07,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_excel_modeling_duration_seconds","value":67.01,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/emb"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_biomysterybench","value":0.8111,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_biomysterybench_cost_per_test_usd","value":3.74,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_biomysterybench_duration_seconds","value":1086,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_biomysterybench","value":0.7963,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_biomysterybench_cost_per_test_usd","value":0.37,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_biomysterybench_duration_seconds","value":531,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_biomysterybench","value":0.7926000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_biomysterybench_cost_per_test_usd","value":1.72,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_biomysterybench_duration_seconds","value":286,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_biomysterybench","value":0.7926000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_biomysterybench_cost_per_test_usd","value":3.64,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_biomysterybench_duration_seconds","value":739,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_biomysterybench","value":0.7926000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_biomysterybench_cost_per_test_usd","value":3.29,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_biomysterybench_duration_seconds","value":2196,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_biomysterybench","value":0.763,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_biomysterybench_cost_per_test_usd","value":5.71,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_biomysterybench_duration_seconds","value":2397,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_biomysterybench","value":0.7481,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_biomysterybench_cost_per_test_usd","value":0.66,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_biomysterybench_duration_seconds","value":324,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_biomysterybench","value":0.7259,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_biomysterybench_cost_per_test_usd","value":1.06,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_biomysterybench_duration_seconds","value":295,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_biomysterybench","value":0.7222,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_biomysterybench_cost_per_test_usd","value":1.23,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_biomysterybench_duration_seconds","value":858,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_biomysterybench","value":0.7111,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_biomysterybench_cost_per_test_usd","value":1.93,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_biomysterybench_duration_seconds","value":1098,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_biomysterybench","value":0.7037,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_biomysterybench_cost_per_test_usd","value":0.51,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_biomysterybench_duration_seconds","value":752,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_biomysterybench","value":0.6926000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_biomysterybench_cost_per_test_usd","value":2.49,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_biomysterybench_duration_seconds","value":697,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_biomysterybench","value":0.6926000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_biomysterybench_cost_per_test_usd","value":0.36,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_biomysterybench_duration_seconds","value":1410,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_biomysterybench","value":0.6926000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_biomysterybench_cost_per_test_usd","value":0.05,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_biomysterybench_duration_seconds","value":1708,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_biomysterybench","value":0.6778,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_biomysterybench_cost_per_test_usd","value":0.23,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_biomysterybench_duration_seconds","value":890,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_biomysterybench","value":0.6740999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_biomysterybench_cost_per_test_usd","value":0.49,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_biomysterybench_duration_seconds","value":1295,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_biomysterybench","value":0.6704000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_biomysterybench_cost_per_test_usd","value":0.91,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_biomysterybench_duration_seconds","value":566,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_biomysterybench","value":0.6704000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_biomysterybench_cost_per_test_usd","value":3.23,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_biomysterybench_duration_seconds","value":1082,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_biomysterybench","value":0.6704000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_biomysterybench_cost_per_test_usd","value":2.07,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_biomysterybench_duration_seconds","value":1532,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_biomysterybench","value":0.6481,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_biomysterybench_cost_per_test_usd","value":0.99,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_biomysterybench_duration_seconds","value":1417,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_biomysterybench","value":0.6444,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_biomysterybench_cost_per_test_usd","value":0.04,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_biomysterybench_duration_seconds","value":1623,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_biomysterybench","value":0.6222,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_biomysterybench_cost_per_test_usd","value":1.55,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_biomysterybench_duration_seconds","value":327,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_biomysterybench","value":0.6148,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_biomysterybench_cost_per_test_usd","value":0.05,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_biomysterybench_duration_seconds","value":524,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_biomysterybench","value":0.6148,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_biomysterybench_cost_per_test_usd","value":0.09,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_biomysterybench_duration_seconds","value":1111,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_biomysterybench","value":0.6,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_biomysterybench_cost_per_test_usd","value":0.71,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_biomysterybench_duration_seconds","value":252,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_biomysterybench","value":0.5852,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_biomysterybench_cost_per_test_usd","value":1.25,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_biomysterybench_duration_seconds","value":762,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/biomysterybench"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_terminal_bench_science","value":0.6286,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":20.8,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":6540,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_terminal_bench_science","value":0.5286,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":3.44,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":4980,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_terminal_bench_science","value":0.4714,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":19.12,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":8880,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_terminal_bench_science","value":0.4714,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":32.52,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":9960,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_terminal_bench_science","value":0.4429,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":44.9,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":6360,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_terminal_bench_science","value":0.4,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":38.01,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":9360,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_terminal_bench_science","value":0.3,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":5.82,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":4920,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_terminal_bench_science","value":0.27140000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":32.54,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":7920,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_terminal_bench_science","value":0.2286,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":19.61,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":5580,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_terminal_bench_science","value":0.2,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":7.32,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":6240,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_terminal_bench_science","value":0.15710000000000002,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":51.99,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":7140,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_terminal_bench_science","value":0.1286,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":16.68,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":12240,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_terminal_bench_science","value":0.1143,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":4.82,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":4680,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_terminal_bench_science","value":0.1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":17.04,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":5580,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_terminal_bench_science","value":0.1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":4.52,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":5640,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_terminal_bench_science","value":0.1,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":5.19,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":7440,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_terminal_bench_science","value":0.0857,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":5.64,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":3311,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_terminal_bench_science","value":0.07139999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":7.19,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":4800,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_terminal_bench_science","value":0.0571,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":3.8,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":3660,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_terminal_bench_science","value":0.0571,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":15.63,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":9900,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_terminal_bench_science","value":0.0571,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":30.3,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":11160,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_terminal_bench_science","value":0.0571,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":30.76,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":12180,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_terminal_bench_science","value":0.0429,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":4.41,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"meta/muse-spark-1.3","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":4080,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_terminal_bench_science","value":0.0429,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":0.24,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":4560,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_terminal_bench_science","value":0.0429,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":1.1,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":5640,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_terminal_bench_science","value":0.0429,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":4.39,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":6720,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_terminal_bench_science","value":0.0429,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":23.14,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":6900,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_terminal_bench_science","value":0.0429,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":4.63,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":8160,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_terminal_bench_science","value":0.0429,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":0.24,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":14340,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_terminal_bench_science","value":0.0286,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":4.25,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":9000,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_terminal_bench_science","value":0.0286,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":0.62,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":11520,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_terminal_bench_science","value":0.0286,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":0.52,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":12480,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_terminal_bench_science","value":0.0143,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":5.91,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":2638,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_terminal_bench_science","value":0.0143,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Terminus 2"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":2.14,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Terminus 2"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":13680,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Terminus 2"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_terminal_bench_science","value":0.0143,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":21.3,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":17340,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_terminal_bench_science","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":0.18,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":1694,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_terminal_bench_science","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":0.58,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":7380,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_terminal_bench_science","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":0.47,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":10620,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_terminal_bench_science","value":0,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_terminal_bench_science_cost_per_test_usd","value":11.14,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_terminal_bench_science_duration_seconds","value":14520,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-science","setting":"Mini-SWE-agent"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_science_index","value":0.6509,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_science_index_cost_per_test_usd","value":8.03,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_science_index_duration_seconds","value":2437,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_science_index","value":0.5963,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_science_index_cost_per_test_usd","value":1.36,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_science_index_duration_seconds","value":1991,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_science_index","value":0.5912,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_science_index_cost_per_test_usd","value":13.24,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_science_index_duration_seconds","value":4140,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_science_index","value":0.5865,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_science_index_cost_per_test_usd","value":9.13,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_science_index_duration_seconds","value":3591,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_science_index","value":0.5536,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_science_index_cost_per_test_usd","value":18.4,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_science_index_duration_seconds","value":3420,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_science_index","value":0.4793,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_science_index_cost_per_test_usd","value":13.04,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_science_index_duration_seconds","value":3720,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_science_index","value":0.45,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_science_index_cost_per_test_usd","value":2.31,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_science_index_duration_seconds","value":1876,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_science_index","value":0.41479999999999995,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_science_index_cost_per_test_usd","value":3.4,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_science_index_duration_seconds","value":2612,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_science_index","value":0.3912,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_science_index_cost_per_test_usd","value":8.74,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_science_index_duration_seconds","value":2588,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_science_index","value":0.385,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_science_index_cost_per_test_usd","value":1.86,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_science_index_duration_seconds","value":2398,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_science_index","value":0.3809,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_science_index_cost_per_test_usd","value":2.45,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_science_index_duration_seconds","value":2410,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_science_index","value":0.3576,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_science_index_cost_per_test_usd","value":2.98,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_science_index_duration_seconds","value":1320,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_science_index","value":0.3483,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_science_index_cost_per_test_usd","value":7.12,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_science_index_duration_seconds","value":2434,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_science_index","value":0.3176,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_science_index_cost_per_test_usd","value":10.99,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_science_index_duration_seconds","value":4680,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_science_index","value":0.3172,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_science_index_cost_per_test_usd","value":0.12,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_science_index_duration_seconds","value":6060,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_science_index","value":0.2965,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_science_index_cost_per_test_usd","value":0.29,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_science_index_duration_seconds","value":4020,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_science_index","value":0.2958,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_science_index_cost_per_test_usd","value":1.78,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_science_index_duration_seconds","value":4020,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_science_index","value":0.2838,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_science_index_cost_per_test_usd","value":0.11,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_science_index_duration_seconds","value":1815,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_science_index","value":0.2738,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_science_index_cost_per_test_usd","value":2.56,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_science_index_duration_seconds","value":1083,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_science_index","value":0.253,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_science_index_cost_per_test_usd","value":0.26,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_science_index_duration_seconds","value":3000,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/science_index"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_time_horizon_index","value":0.9133,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/time_horizon_index"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_time_horizon_index","value":0.905,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/time_horizon_index"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_time_horizon_index","value":0.6333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/time_horizon_index"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_time_horizon_index","value":0.525,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/time_horizon_index"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_time_horizon_index","value":0.23829999999999998,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/time_horizon_index"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_time_horizon_index","value":0.1883,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/time_horizon_index"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_time_horizon_index","value":0.1883,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/time_horizon_index"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_time_horizon_index","value":0.1183,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/time_horizon_index"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_time_horizon_index","value":0.105,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/time_horizon_index"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_time_horizon_index","value":0.0833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/time_horizon_index"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_time_horizon_index","value":0.0633,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/time_horizon_index"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_time_horizon_index","value":0.0583,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/time_horizon_index"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_time_horizon_index","value":0.0167,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/time_horizon_index"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_cua_bench","value":0.1917,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cua_bench"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_cua_bench","value":0.14,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cua_bench"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_cua_bench","value":0.1317,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cua_bench"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_cua_bench","value":0.09,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cua_bench"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_cua_bench","value":0.0833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cua_bench"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_cua_bench","value":0.0717,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cua_bench"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_cua_bench","value":0.0483,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cua_bench"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_cua_bench","value":0.0417,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/cua_bench"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_robo_bench","value":0.2833,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/robo_bench"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_robo_bench","value":0.23329999999999998,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/robo_bench"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_robo_bench","value":0.1458,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/robo_bench"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_robo_bench","value":0.0583,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/robo_bench"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_robo_bench","value":0.0083,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/robo_bench"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_robo_bench","value":0.0021,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/robo_bench"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_public_benefits","value":0.7693000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":3.95,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_public_benefits","value":0.7490000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":7.48,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_public_benefits","value":0.7064,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":5.95,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_public_benefits","value":0.7043,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":4.59,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_public_benefits","value":0.7023,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":2.46,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_public_benefits","value":0.6976,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":2.79,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_public_benefits","value":0.6894,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":0.08,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_public_benefits","value":0.6861,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":0.25,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_public_benefits","value":0.6854,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":0.95,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_public_benefits","value":0.6847,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":0.59,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_public_benefits","value":0.682,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":0.91,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_public_benefits","value":0.6812999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":1.89,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_public_benefits","value":0.6759000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":0.03,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_public_benefits","value":0.6718999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":4.25,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_public_benefits","value":0.6712,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":0.99,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_public_benefits","value":0.6685,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":0.92,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_public_benefits","value":0.6651,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":8.85,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_public_benefits","value":0.6617000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":1.02,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_public_benefits","value":0.6603,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":1.29,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_public_benefits","value":0.6563,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":2.25,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_public_benefits","value":0.6529,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":1.01,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_public_benefits","value":0.6428,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":0.07,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_public_benefits","value":0.6414,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":0.25,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_public_benefits","value":0.6319,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":0.53,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_public_benefits","value":0.6292,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":0.46,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_public_benefits","value":0.6245,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":1.11,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_public_benefits","value":0.6238,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":1.2,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_public_benefits","value":0.6184000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":0.34,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_public_benefits","value":0.613,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":0.28,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_public_benefits","value":0.6115999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":0.27,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_public_benefits","value":0.6089,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":3.97,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_public_benefits","value":0.5947,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":1.11,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_public_benefits","value":0.5941,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":0.1,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_public_benefits","value":0.5934,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":0.69,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_public_benefits","value":0.5846,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":0.37,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_public_benefits","value":0.5811999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":0.5,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_public_benefits","value":0.5765,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":0.22,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_public_benefits","value":0.5663,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":0.91,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_public_benefits","value":0.5663,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":2.49,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_public_benefits","value":0.5656,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":0.39,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_public_benefits","value":0.5426,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":0.22,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_public_benefits","value":0.5379,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":0.38,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_public_benefits","value":0.5183,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":0.1,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_public_benefits","value":0.5169,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":0.26,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_public_benefits","value":0.5074000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":0.05,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_public_benefits","value":0.4526,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_public_benefits_cost_per_test_usd","value":0.07,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/public-benefits-bench"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_mysterymechanism","value":0.5315,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_mysterymechanism_cost_per_test_usd","value":1.56,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_mysterymechanism_duration_seconds","value":489,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_mysterymechanism","value":0.4955,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_mysterymechanism_cost_per_test_usd","value":4.62,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_mysterymechanism_duration_seconds","value":1178,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_mysterymechanism","value":0.491,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_mysterymechanism_cost_per_test_usd","value":3.45,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_mysterymechanism_duration_seconds","value":1410,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_mysterymechanism","value":0.4775,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_mysterymechanism_cost_per_test_usd","value":5.63,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_mysterymechanism_duration_seconds","value":1061,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_mysterymechanism","value":0.46399999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_mysterymechanism_cost_per_test_usd","value":0.28,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_mysterymechanism_duration_seconds","value":437,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_mysterymechanism","value":0.4549,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_mysterymechanism_cost_per_test_usd","value":4.59,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_mysterymechanism_duration_seconds","value":1495,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_mysterymechanism","value":0.3739,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_mysterymechanism_cost_per_test_usd","value":3.28,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_mysterymechanism_duration_seconds","value":1013,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_mysterymechanism","value":0.3649,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_mysterymechanism_cost_per_test_usd","value":1.73,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_mysterymechanism_duration_seconds","value":322,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_mysterymechanism","value":0.3513,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_mysterymechanism_cost_per_test_usd","value":0.54,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_mysterymechanism_duration_seconds","value":805,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_mysterymechanism","value":0.3333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_mysterymechanism_cost_per_test_usd","value":0.96,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_mysterymechanism_duration_seconds","value":523,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_mysterymechanism","value":0.3063,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_mysterymechanism_cost_per_test_usd","value":1.31,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_mysterymechanism_duration_seconds","value":1675,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_mysterymechanism","value":0.3018,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_mysterymechanism_cost_per_test_usd","value":0.46,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_mysterymechanism_duration_seconds","value":373,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_mysterymechanism","value":0.2748,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_mysterymechanism_cost_per_test_usd","value":3.39,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"meta/muse-wonder","source":"vals-more","metric":"vals_mysterymechanism_duration_seconds","value":1097,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_mysterymechanism","value":0.2523,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_mysterymechanism_cost_per_test_usd","value":1.84,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_mysterymechanism_duration_seconds","value":1053,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_mysterymechanism","value":0.23870000000000002,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_mysterymechanism_cost_per_test_usd","value":1.31,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_mysterymechanism_duration_seconds","value":2269,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_mysterymechanism","value":0.2297,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_mysterymechanism_cost_per_test_usd","value":1.53,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_mysterymechanism_duration_seconds","value":1842,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_mysterymechanism","value":0.22519999999999998,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_mysterymechanism_cost_per_test_usd","value":1.29,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"fireworks/ember-1","source":"vals-more","metric":"vals_mysterymechanism_duration_seconds","value":1215,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_mysterymechanism","value":0.2162,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_mysterymechanism_cost_per_test_usd","value":0.06,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_mysterymechanism_duration_seconds","value":2108,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_mysterymechanism","value":0.21170000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_mysterymechanism_cost_per_test_usd","value":0.16,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_mysterymechanism_duration_seconds","value":484,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_mysterymechanism","value":0.2072,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_mysterymechanism_cost_per_test_usd","value":1.07,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_mysterymechanism_duration_seconds","value":360,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_mysterymechanism","value":0.1937,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_mysterymechanism_cost_per_test_usd","value":0.03,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_mysterymechanism_duration_seconds","value":361,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_mysterymechanism","value":0.18469999999999998,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_mysterymechanism_cost_per_test_usd","value":0.6,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"stepfun/step-5-preview","source":"vals-more","metric":"vals_mysterymechanism_duration_seconds","value":1760,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_mysterymechanism","value":0.1531,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_mysterymechanism_cost_per_test_usd","value":0.15,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_mysterymechanism_duration_seconds","value":2640,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_mysterymechanism","value":0.1441,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_mysterymechanism_cost_per_test_usd","value":0.11,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_mysterymechanism_duration_seconds","value":493,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_mysterymechanism","value":0.1216,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_mysterymechanism_cost_per_test_usd","value":2.1,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_mysterymechanism_duration_seconds","value":2137,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mysterymechanism"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_mmmu_pro","value":0.9064,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":37.47,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_mmmu_pro","value":0.8987999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":30.03,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_mmmu_pro","value":0.8931,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":61.44,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_mmmu_pro","value":0.8908,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":12.03,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_mmmu_pro","value":0.8896,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":6.28,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_mmmu_pro","value":0.8884000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":26.2,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_mmmu_pro","value":0.8837999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":11.31,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_mmmu_pro","value":0.8826999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":12.23,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_mmmu_pro","value":0.8826999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":54.15,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_mmmu_pro","value":0.8820999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":76.99,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_mmmu_pro","value":0.8815000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":106.52,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_mmmu_pro","value":0.8803,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":43.85,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_mmmu_pro","value":0.8763,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":27.86,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_mmmu_pro","value":0.8751000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":65.56,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-5.2","source":"vals-more","metric":"vals_mmmu_pro","value":0.8667,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-5.2","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":96.32,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_mmmu_pro","value":0.8659,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":31.71,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_mmmu_pro","value":0.8659,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":49.04,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_mmmu_pro","value":0.8647,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":13.03,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_mmmu_pro","value":0.863,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":242,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_mmmu_pro","value":0.8613,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":73.84,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_mmmu_pro","value":0.8601000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":28.22,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_mmmu_pro","value":0.8554999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":70.8,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_mmmu_pro","value":0.8503000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":35.1,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_mmmu_pro","value":0.8432999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":110.01,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_mmmu_pro","value":0.8416,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":111.94,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_mmmu_pro","value":0.8393,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":43.48,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"anthropic/claude-opus-4.6","source":"vals-more","metric":"vals_mmmu_pro","value":0.8387,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"anthropic/claude-opus-4.6","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":119,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_mmmu_pro","value":0.8358,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":7.8,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_mmmu_pro","value":0.8358,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":132,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_mmmu_pro","value":0.8347,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":44.46,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-5.1","source":"vals-more","metric":"vals_mmmu_pro","value":0.8318000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-5.1","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":75.31,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_mmmu_pro","value":0.8306,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":151,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_mmmu_pro","value":0.8301000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":18.82,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-more","metric":"vals_mmmu_pro","value":0.8295,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":75.28,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_mmmu_pro","value":0.8249,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":12.45,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"vals-more","metric":"vals_mmmu_pro","value":0.8190999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":45.84,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-5","source":"vals-more","metric":"vals_mmmu_pro","value":0.815,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-5","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":72.11,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_mmmu_pro","value":0.8116,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":68.35,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/o3","source":"vals-more","metric":"vals_mmmu_pro","value":0.8042,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/o3","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":39.27,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_mmmu_pro","value":0.8,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":42.47,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/o4-mini","source":"vals-more","metric":"vals_mmmu_pro","value":0.7967,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/o4-mini","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":19.72,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-more","metric":"vals_mmmu_pro","value":0.7931,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":56.36,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_mmmu_pro","value":0.7925,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":50.81,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-5-mini","source":"vals-more","metric":"vals_mmmu_pro","value":0.7890999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-5-mini","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":26.7,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_mmmu_pro","value":0.785,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":124,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"anthropic/claude-opus-4.1","source":"vals-more","metric":"vals_mmmu_pro","value":0.7751,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"anthropic/claude-opus-4.1","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":2.45,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/o1","source":"vals-more","metric":"vals_mmmu_pro","value":0.7741,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/o1","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":26.41,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"google/gemini-2.5-flash-lite","source":"vals-more","metric":"vals_mmmu_pro","value":0.7543000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"google/gemini-2.5-flash-lite","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":25.73,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_mmmu_pro","value":0.7358,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":21.91,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-4.1","source":"vals-more","metric":"vals_mmmu_pro","value":0.7239,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-4.1","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":12,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"meta-llama/llama-4-maverick","source":"vals-more","metric":"vals_mmmu_pro","value":0.7169,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"meta-llama/llama-4-maverick","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":7.91,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-5-nano","source":"vals-more","metric":"vals_mmmu_pro","value":0.7094,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-5-nano","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":30.78,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-4.1-mini","source":"vals-more","metric":"vals_mmmu_pro","value":0.7054,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-4.1-mini","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":8.22,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"mistralai/mistral-large-2512","source":"vals-more","metric":"vals_mmmu_pro","value":0.6618999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"mistralai/mistral-large-2512","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":13.55,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-4o-2024-08-06","source":"vals-more","metric":"vals_mmmu_pro","value":0.6401,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-4o-2024-08-06","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":47.52,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"mistralai/mistral-medium-3.1","source":"vals-more","metric":"vals_mmmu_pro","value":0.6297,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"mistralai/mistral-medium-3.1","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":12.56,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-4o-2024-11-20","source":"vals-more","metric":"vals_mmmu_pro","value":0.6215999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-4o-2024-11-20","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":45.87,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_mmmu_pro","value":0.6179,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":715,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"meta-llama/llama-4-scout","source":"vals-more","metric":"vals_mmmu_pro","value":0.5875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"meta-llama/llama-4-scout","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":10.51,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-4o-mini","source":"vals-more","metric":"vals_mmmu_pro","value":0.5656,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-4o-mini","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":45.02,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-4.1-nano","source":"vals-more","metric":"vals_mmmu_pro","value":0.5505,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-4.1-nano","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":7.25,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_mmmu_pro","value":0.4607,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":40.48,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"vals-more","metric":"vals_mmmu_pro","value":0.22769999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"vals-more","metric":"vals_mmmu_pro_latency_seconds","value":135,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mmmu"},{"modelId":"openai/gpt-5","source":"vals-more","metric":"vals_math_500","value":0.96,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"openai/gpt-5","source":"vals-more","metric":"vals_math_500_latency_seconds","value":32.22,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"anthropic/claude-opus-4.1","source":"vals-more","metric":"vals_math_500","value":0.9540000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"anthropic/claude-opus-4.1","source":"vals-more","metric":"vals_math_500_latency_seconds","value":45.98,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"openai/gpt-5-mini","source":"vals-more","metric":"vals_math_500","value":0.948,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"openai/gpt-5-mini","source":"vals-more","metric":"vals_math_500_latency_seconds","value":12.06,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"openai/gpt-oss-120b","source":"vals-more","metric":"vals_math_500","value":0.948,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"openai/gpt-oss-120b","source":"vals-more","metric":"vals_math_500_latency_seconds","value":16.27,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"openai/o3","source":"vals-more","metric":"vals_math_500","value":0.946,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"openai/o3","source":"vals-more","metric":"vals_math_500_latency_seconds","value":16.59,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"openai/o4-mini","source":"vals-more","metric":"vals_math_500","value":0.9420000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"openai/o4-mini","source":"vals-more","metric":"vals_math_500_latency_seconds","value":12.54,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"openai/gpt-oss-20b","source":"vals-more","metric":"vals_math_500","value":0.9420000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"openai/gpt-oss-20b","source":"vals-more","metric":"vals_math_500_latency_seconds","value":31.47,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"moonshotai/kimi-k2","source":"vals-more","metric":"vals_math_500","value":0.9420000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"moonshotai/kimi-k2","source":"vals-more","metric":"vals_math_500_latency_seconds","value":37.35,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"z-ai/glm-4.5","source":"vals-more","metric":"vals_math_500","value":0.94,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"z-ai/glm-4.5","source":"vals-more","metric":"vals_math_500_latency_seconds","value":84.93,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"openai/gpt-5-nano","source":"vals-more","metric":"vals_math_500","value":0.938,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"openai/gpt-5-nano","source":"vals-more","metric":"vals_math_500_latency_seconds","value":22.4,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"openai/o3-mini","source":"vals-more","metric":"vals_math_500","value":0.9179999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"openai/o3-mini","source":"vals-more","metric":"vals_math_500_latency_seconds","value":14.37,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"openai/o1","source":"vals-more","metric":"vals_math_500","value":0.904,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"openai/o1","source":"vals-more","metric":"vals_math_500_latency_seconds","value":23.54,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"minimax/minimax-m2.1","source":"vals-more","metric":"vals_math_500","value":0.89,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"minimax/minimax-m2.1","source":"vals-more","metric":"vals_math_500_latency_seconds","value":59.69,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"vals-more","metric":"vals_math_500","value":0.8859999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"vals-more","metric":"vals_math_500_latency_seconds","value":12.54,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"openai/gpt-4.1-mini","source":"vals-more","metric":"vals_math_500","value":0.88,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"openai/gpt-4.1-mini","source":"vals-more","metric":"vals_math_500_latency_seconds","value":5.76,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"openai/gpt-4.1","source":"vals-more","metric":"vals_math_500","value":0.872,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"openai/gpt-4.1","source":"vals-more","metric":"vals_math_500_latency_seconds","value":12.53,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"mistralai/mistral-medium-3.1","source":"vals-more","metric":"vals_math_500","value":0.87,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"mistralai/mistral-medium-3.1","source":"vals-more","metric":"vals_math_500_latency_seconds","value":14.13,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"meta-llama/llama-4-maverick","source":"vals-more","metric":"vals_math_500","value":0.852,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"meta-llama/llama-4-maverick","source":"vals-more","metric":"vals_math_500_latency_seconds","value":7.47,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"openai/gpt-4.1-nano","source":"vals-more","metric":"vals_math_500","value":0.802,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"openai/gpt-4.1-nano","source":"vals-more","metric":"vals_math_500_latency_seconds","value":3.37,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"meta-llama/llama-4-scout","source":"vals-more","metric":"vals_math_500","value":0.792,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"meta-llama/llama-4-scout","source":"vals-more","metric":"vals_math_500_latency_seconds","value":10.52,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"cohere/command-a","source":"vals-more","metric":"vals_math_500","value":0.762,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"cohere/command-a","source":"vals-more","metric":"vals_math_500_latency_seconds","value":8.66,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"openai/gpt-4o-2024-08-06","source":"vals-more","metric":"vals_math_500","value":0.752,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"openai/gpt-4o-2024-08-06","source":"vals-more","metric":"vals_math_500_latency_seconds","value":12.29,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"mistralai/mistral-large","source":"vals-more","metric":"vals_math_500","value":0.7440000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"mistralai/mistral-large","source":"vals-more","metric":"vals_math_500_latency_seconds","value":9.93,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"openai/gpt-4o-2024-11-20","source":"vals-more","metric":"vals_math_500","value":0.74,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"openai/gpt-4o-2024-11-20","source":"vals-more","metric":"vals_math_500_latency_seconds","value":12.8,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"openai/gpt-4o-mini","source":"vals-more","metric":"vals_math_500","value":0.726,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"openai/gpt-4o-mini","source":"vals-more","metric":"vals_math_500_latency_seconds","value":6.3,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/math500"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-more","metric":"vals_mgsm","value":0.9520000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":11.56,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"anthropic/claude-opus-4.1","source":"vals-more","metric":"vals_mgsm","value":0.9444,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"anthropic/claude-opus-4.1","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":14.28,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-more","metric":"vals_mgsm","value":0.9433,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":10.27,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"openai/gpt-5.2","source":"vals-more","metric":"vals_mgsm","value":0.94,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"openai/gpt-5.2","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":10.6,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"openai/o4-mini","source":"vals-more","metric":"vals_mgsm","value":0.9342,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"openai/o4-mini","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":8.07,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_mgsm","value":0.9331,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":14.02,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"openai/gpt-5.1","source":"vals-more","metric":"vals_mgsm","value":0.9298000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"openai/gpt-5.1","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":8.35,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"openai/gpt-5","source":"vals-more","metric":"vals_mgsm","value":0.9284,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"openai/gpt-5","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":20.35,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"openai/gpt-5-mini","source":"vals-more","metric":"vals_mgsm","value":0.9258,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"openai/gpt-5-mini","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":12.57,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"meta-llama/llama-4-maverick","source":"vals-more","metric":"vals_mgsm","value":0.9244,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"meta-llama/llama-4-maverick","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":2.71,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_mgsm","value":0.9215000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":9.62,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"openai/gpt-oss-120b","source":"vals-more","metric":"vals_mgsm","value":0.9204000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"openai/gpt-oss-120b","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":5.79,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"openai/o3","source":"vals-more","metric":"vals_mgsm","value":0.9175,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"openai/o3","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":6.76,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"vals-more","metric":"vals_mgsm","value":0.9167000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":18.03,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"openai/o3-mini","source":"vals-more","metric":"vals_mgsm","value":0.9135,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"openai/o3-mini","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":15.98,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"moonshotai/kimi-k2","source":"vals-more","metric":"vals_mgsm","value":0.9095,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"moonshotai/kimi-k2","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":11.83,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"mistralai/mistral-medium-3.1","source":"vals-more","metric":"vals_mgsm","value":0.9087000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"mistralai/mistral-medium-3.1","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":5.01,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"z-ai/glm-4.5","source":"vals-more","metric":"vals_mgsm","value":0.9084,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"z-ai/glm-4.5","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":89.55,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"openai/gpt-4o-2024-08-06","source":"vals-more","metric":"vals_mgsm","value":0.9068999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"openai/gpt-4o-2024-08-06","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":6.73,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"openai/gpt-4o-2024-11-20","source":"vals-more","metric":"vals_mgsm","value":0.9036,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"openai/gpt-4o-2024-11-20","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":3.98,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"moonshotai/kimi-k2-thinking","source":"vals-more","metric":"vals_mgsm","value":0.9015000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"moonshotai/kimi-k2-thinking","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":48.41,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"z-ai/glm-4.6","source":"vals-more","metric":"vals_mgsm","value":0.8975,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"z-ai/glm-4.6","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":34.31,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"google/gemini-2.5-flash-lite","source":"vals-more","metric":"vals_mgsm","value":0.8953,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"google/gemini-2.5-flash-lite","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":1.47,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"openai/o1","source":"vals-more","metric":"vals_mgsm","value":0.8931,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"openai/o1","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":11.21,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"openai/gpt-5-nano","source":"vals-more","metric":"vals_mgsm","value":0.8931,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"openai/gpt-5-nano","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":22.77,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"openai/gpt-oss-20b","source":"vals-more","metric":"vals_mgsm","value":0.8902,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"openai/gpt-oss-20b","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":5.79,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"z-ai/glm-4.7","source":"vals-more","metric":"vals_mgsm","value":0.8818,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"z-ai/glm-4.7","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":63.17,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"meta-llama/llama-4-scout","source":"vals-more","metric":"vals_mgsm","value":0.8795999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"meta-llama/llama-4-scout","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":3.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"minimax/minimax-m2.1","source":"vals-more","metric":"vals_mgsm","value":0.8785,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"minimax/minimax-m2.1","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":13.86,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"openai/gpt-4.1-mini","source":"vals-more","metric":"vals_mgsm","value":0.8778,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"openai/gpt-4.1-mini","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":2.75,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"openai/gpt-4.1","source":"vals-more","metric":"vals_mgsm","value":0.8767,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"openai/gpt-4.1","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":2.19,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"mistralai/mistral-large","source":"vals-more","metric":"vals_mgsm","value":0.8724,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"mistralai/mistral-large","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":8.04,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"openai/gpt-4o-mini","source":"vals-more","metric":"vals_mgsm","value":0.8618000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"openai/gpt-4o-mini","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":4.03,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"deepseek/deepseek-v3.2","source":"vals-more","metric":"vals_mgsm","value":0.8604,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"deepseek/deepseek-v3.2","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":28.22,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"cohere/command-a","source":"vals-more","metric":"vals_mgsm","value":0.8571,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"cohere/command-a","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":8.36,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"mistralai/mistral-large-2512","source":"vals-more","metric":"vals_mgsm","value":0.8542000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"mistralai/mistral-large-2512","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":7.62,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"openai/gpt-4.1-nano","source":"vals-more","metric":"vals_mgsm","value":0.6927,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"openai/gpt-4.1-nano","source":"vals-more","metric":"vals_mgsm_latency_seconds","value":1.46,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mgsm"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_sage","value":0.561,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_sage_latency_seconds","value":125,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"google/gemma-4-31b-it","source":"vals-more","metric":"vals_sage","value":0.5503,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"google/gemma-4-31b-it","source":"vals-more","metric":"vals_sage_latency_seconds","value":93.06,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_sage","value":0.5478999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_sage_latency_seconds","value":186,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_sage","value":0.5365,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_sage_latency_seconds","value":63.07,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_sage","value":0.5278,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_sage_latency_seconds","value":47.3,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_sage","value":0.5256000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_sage_latency_seconds","value":75.39,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_sage","value":0.524,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_sage_latency_seconds","value":83.03,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-more","metric":"vals_sage","value":0.5209,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-more","metric":"vals_sage_latency_seconds","value":87.22,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_sage","value":0.5189,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_sage_latency_seconds","value":116.92,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_sage","value":0.5185,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_sage_latency_seconds","value":42.7,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_sage","value":0.5177,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_sage_latency_seconds","value":113.42,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"anthropic/claude-opus-4.6","source":"vals-more","metric":"vals_sage","value":0.5158,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"anthropic/claude-opus-4.6","source":"vals-more","metric":"vals_sage_latency_seconds","value":161,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_sage","value":0.5153,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_sage_latency_seconds","value":76.05,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_sage","value":0.5125,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_sage_latency_seconds","value":133,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_sage","value":0.5081,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_sage_latency_seconds","value":141,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_sage","value":0.5057,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_sage_latency_seconds","value":118.54,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_sage","value":0.5022,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_sage_latency_seconds","value":271,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_sage","value":0.4988,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_sage_latency_seconds","value":32.59,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_sage","value":0.4987,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_sage_latency_seconds","value":173,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_sage","value":0.4954,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_sage_latency_seconds","value":16.26,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_sage","value":0.4943,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_sage_latency_seconds","value":56.17,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/gpt-5.2","source":"vals-more","metric":"vals_sage","value":0.4927,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/gpt-5.2","source":"vals-more","metric":"vals_sage_latency_seconds","value":179,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_sage","value":0.49229999999999996,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_sage_latency_seconds","value":9.79,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_sage","value":0.4892,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_sage_latency_seconds","value":434,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_sage","value":0.4869,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_sage_latency_seconds","value":21.96,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_sage","value":0.4868,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_sage_latency_seconds","value":61.17,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_sage","value":0.4853,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_sage_latency_seconds","value":105.75,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_sage","value":0.48090000000000005,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_sage_latency_seconds","value":91.07,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_sage","value":0.4788,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_sage_latency_seconds","value":35.78,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_sage","value":0.47659999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_sage_latency_seconds","value":29.07,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_sage","value":0.473,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_sage_latency_seconds","value":10.75,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_sage","value":0.47,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_sage_latency_seconds","value":40.06,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_sage","value":0.4658,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_sage_latency_seconds","value":163,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_sage","value":0.4654,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_sage_latency_seconds","value":50.22,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_sage","value":0.4637,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_sage_latency_seconds","value":41.63,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_sage","value":0.4583,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_sage_latency_seconds","value":114.2,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_sage","value":0.4578,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_sage_latency_seconds","value":143,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_sage","value":0.4558,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_sage_latency_seconds","value":49.95,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"qwen/qwen3.6-27b","source":"vals-more","metric":"vals_sage","value":0.4558,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"qwen/qwen3.6-27b","source":"vals-more","metric":"vals_sage_latency_seconds","value":159,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_sage","value":0.45049999999999996,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_sage_latency_seconds","value":220,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_sage","value":0.4486,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_sage_latency_seconds","value":229,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_sage","value":0.44789999999999996,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_sage_latency_seconds","value":31.42,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"google/gemini-2.5-flash","source":"vals-more","metric":"vals_sage","value":0.4476,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"google/gemini-2.5-flash","source":"vals-more","metric":"vals_sage_latency_seconds","value":40.21,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_sage","value":0.4422,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_sage_latency_seconds","value":51.88,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/gpt-5","source":"vals-more","metric":"vals_sage","value":0.4368,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/gpt-5","source":"vals-more","metric":"vals_sage_latency_seconds","value":58.59,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_sage","value":0.4353,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_sage_latency_seconds","value":136,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_sage","value":0.43310000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_sage_latency_seconds","value":152,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_sage","value":0.43270000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_sage_latency_seconds","value":52.66,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/gpt-5.1","source":"vals-more","metric":"vals_sage","value":0.43229999999999996,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/gpt-5.1","source":"vals-more","metric":"vals_sage_latency_seconds","value":98.21,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/gpt-5-mini","source":"vals-more","metric":"vals_sage","value":0.4299,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/gpt-5-mini","source":"vals-more","metric":"vals_sage_latency_seconds","value":36.52,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"vals-more","metric":"vals_sage","value":0.4249,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"vals-more","metric":"vals_sage_latency_seconds","value":85.04,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"google/gemini-2.5-pro","source":"vals-more","metric":"vals_sage","value":0.4192,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"google/gemini-2.5-pro","source":"vals-more","metric":"vals_sage_latency_seconds","value":52.93,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/o3","source":"vals-more","metric":"vals_sage","value":0.4177,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/o3","source":"vals-more","metric":"vals_sage_latency_seconds","value":48.02,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/o4-mini","source":"vals-more","metric":"vals_sage","value":0.4106,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/o4-mini","source":"vals-more","metric":"vals_sage_latency_seconds","value":27.21,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_sage","value":0.4079,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_sage_latency_seconds","value":291,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"qwen/qwen3.7-plus","source":"vals-more","metric":"vals_sage","value":0.3925,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"qwen/qwen3.7-plus","source":"vals-more","metric":"vals_sage_latency_seconds","value":177,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_sage","value":0.3824,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_sage_latency_seconds","value":66.36,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_sage","value":0.38079999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_sage_latency_seconds","value":34.33,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_sage","value":0.3761,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_sage_latency_seconds","value":55.84,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_sage","value":0.3655,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_sage_latency_seconds","value":198,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-more","metric":"vals_sage","value":0.36060000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-more","metric":"vals_sage_latency_seconds","value":210,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"meta-llama/llama-4-maverick","source":"vals-more","metric":"vals_sage","value":0.35700000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"meta-llama/llama-4-maverick","source":"vals-more","metric":"vals_sage_latency_seconds","value":43.59,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_sage","value":0.3506,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_sage_latency_seconds","value":28.64,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_sage","value":0.3497,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_sage_latency_seconds","value":170,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"meta-llama/llama-4-scout","source":"vals-more","metric":"vals_sage","value":0.3483,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"meta-llama/llama-4-scout","source":"vals-more","metric":"vals_sage_latency_seconds","value":32.86,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_sage","value":0.3274,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_sage_latency_seconds","value":206,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_sage","value":0.3182,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_sage_latency_seconds","value":66.44,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"anthropic/claude-opus-4.1","source":"vals-more","metric":"vals_sage","value":0.31379999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"anthropic/claude-opus-4.1","source":"vals-more","metric":"vals_sage_latency_seconds","value":17.33,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"google/gemini-2.5-flash-lite","source":"vals-more","metric":"vals_sage","value":0.3078,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"google/gemini-2.5-flash-lite","source":"vals-more","metric":"vals_sage_latency_seconds","value":32.94,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"vals-more","metric":"vals_sage","value":0.304,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"vals-more","metric":"vals_sage_latency_seconds","value":313,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/gpt-5-nano","source":"vals-more","metric":"vals_sage","value":0.3038,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"openai/gpt-5-nano","source":"vals-more","metric":"vals_sage_latency_seconds","value":38.71,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_sage","value":0.289,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_sage_latency_seconds","value":202,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"mistralai/mistral-large-2512","source":"vals-more","metric":"vals_sage","value":0.2459,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"mistralai/mistral-large-2512","source":"vals-more","metric":"vals_sage_latency_seconds","value":55.07,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_sage","value":0.1974,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_sage_latency_seconds","value":96.2,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/sage"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_legalbench","value":0.8856,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":8.96,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_legalbench","value":0.8851,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":12.4,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_legalbench","value":0.883,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":12.62,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_legalbench","value":0.8740000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":10.06,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_legalbench","value":0.8726,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":2.23,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_legalbench","value":0.8698999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":3.32,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_legalbench","value":0.8697,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":4.42,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_legalbench","value":0.8697,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":6.2,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_legalbench","value":0.8686,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":4.67,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_legalbench","value":0.867,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":2.96,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_legalbench","value":0.8652,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":18.14,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_legalbench","value":0.8631,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":27.42,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_legalbench","value":0.8621,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":7.11,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_legalbench","value":0.8604,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":27.79,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-5","source":"vals-more","metric":"vals_legalbench","value":0.8602,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-5","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":18.59,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_legalbench","value":0.8597,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":67.88,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-5.1","source":"vals-more","metric":"vals_legalbench","value":0.8568000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-5.1","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":7.05,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_legalbench","value":0.8542000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":8.21,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"anthropic/claude-opus-4.6","source":"vals-more","metric":"vals_legalbench","value":0.853,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"anthropic/claude-opus-4.6","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":3.75,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_legalbench","value":0.8526,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":30.1,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_legalbench","value":0.8525,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":26.62,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_legalbench","value":0.8511,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":2.78,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"vals-more","metric":"vals_legalbench","value":0.851,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":30.42,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_legalbench","value":0.8498,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":17.15,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_legalbench","value":0.8491,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":11.85,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_legalbench","value":0.8484,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":22.48,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_legalbench","value":0.8473999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":50.07,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-more","metric":"vals_legalbench","value":0.846,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":7.64,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_legalbench","value":0.8445999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":348,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_legalbench","value":0.8439,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":13.75,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_legalbench","value":0.8439,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":26.02,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"vals-more","metric":"vals_legalbench","value":0.8428,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":16.73,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_legalbench","value":0.8423,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":19.07,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-more","metric":"vals_legalbench","value":0.8408,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":13.29,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_legalbench","value":0.8406999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":1.67,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_legalbench","value":0.8406999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":5.77,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"z-ai/glm-5","source":"vals-more","metric":"vals_legalbench","value":0.8406,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"z-ai/glm-5","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":16.06,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_legalbench","value":0.8403,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":5.89,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_legalbench","value":0.8398,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":8.92,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_legalbench","value":0.8393,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":12.52,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_legalbench","value":0.8392000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":4.9,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_legalbench","value":0.8376,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":2.7,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/o3","source":"vals-more","metric":"vals_legalbench","value":0.8376,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/o3","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":5.98,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_legalbench","value":0.8376,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":90.56,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_legalbench","value":0.8361,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":36.37,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_legalbench","value":0.836,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":34.58,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_legalbench","value":0.8356999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":3.11,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"anthropic/claude-opus-4.1","source":"vals-more","metric":"vals_legalbench","value":0.8345999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"anthropic/claude-opus-4.1","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":2.79,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"z-ai/glm-4.7","source":"vals-more","metric":"vals_legalbench","value":0.8336,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"z-ai/glm-4.7","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":30.68,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_legalbench","value":0.8328,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":6.53,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-4.1","source":"vals-more","metric":"vals_legalbench","value":0.831,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-4.1","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":0.51,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_legalbench","value":0.8306,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":3.91,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_legalbench","value":0.8299,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":17.66,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_legalbench","value":0.8295,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":23.14,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-5.2","source":"vals-more","metric":"vals_legalbench","value":0.8276,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-5.2","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":17.14,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_legalbench","value":0.8243,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":47.81,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_legalbench","value":0.8236,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":20.05,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-4o-2024-11-20","source":"vals-more","metric":"vals_legalbench","value":0.8220999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-4o-2024-11-20","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":0.45,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_legalbench","value":0.8212,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":21.63,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"vals-more","metric":"vals_legalbench","value":0.8207,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":5.18,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"google/gemini-2.5-flash-lite","source":"vals-more","metric":"vals_legalbench","value":0.8204,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"google/gemini-2.5-flash-lite","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":3.14,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-5-mini","source":"vals-more","metric":"vals_legalbench","value":0.8177,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-5-mini","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":9.43,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"moonshotai/kimi-k2","source":"vals-more","metric":"vals_legalbench","value":0.8145,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"moonshotai/kimi-k2","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":1.17,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_legalbench","value":0.8123999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":10.37,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-4-turbo","source":"vals-more","metric":"vals_legalbench","value":0.8046,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-4-turbo","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":1.41,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/o1","source":"vals-more","metric":"vals_legalbench","value":0.8039000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/o1","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":8.34,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_legalbench","value":0.8031999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":184,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"moonshotai/kimi-k2-thinking","source":"vals-more","metric":"vals_legalbench","value":0.802,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"moonshotai/kimi-k2-thinking","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":43.99,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-4o-2024-08-06","source":"vals-more","metric":"vals_legalbench","value":0.8012,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-4o-2024-08-06","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":0.53,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"minimax/minimax-m2.5","source":"vals-more","metric":"vals_legalbench","value":0.7996,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"minimax/minimax-m2.5","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":15.82,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"cohere/command-a","source":"vals-more","metric":"vals_legalbench","value":0.797,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"cohere/command-a","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":0.8,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_legalbench","value":0.7968999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":3.9,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"z-ai/glm-4.6","source":"vals-more","metric":"vals_legalbench","value":0.7961,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"z-ai/glm-4.6","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":29.82,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/o4-mini","source":"vals-more","metric":"vals_legalbench","value":0.7918999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/o4-mini","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":4.03,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"mistralai/mistral-large-2512","source":"vals-more","metric":"vals_legalbench","value":0.7914,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"mistralai/mistral-large-2512","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":1.73,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_legalbench","value":0.7889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":11.18,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-4.1-mini","source":"vals-more","metric":"vals_legalbench","value":0.7804000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-4.1-mini","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":0.47,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_legalbench","value":0.7792,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":2.7,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"meta-llama/llama-4-maverick","source":"vals-more","metric":"vals_legalbench","value":0.7781,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"meta-llama/llama-4-maverick","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":0.47,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_legalbench","value":0.7774,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":7.57,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"vals-more","metric":"vals_legalbench","value":0.7773,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":7.71,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_legalbench","value":0.7770999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":3.95,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_legalbench","value":0.7713,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":27.14,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"deepseek/deepseek-v3.2","source":"vals-more","metric":"vals_legalbench","value":0.7608,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"deepseek/deepseek-v3.2","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":31.47,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-oss-120b","source":"vals-more","metric":"vals_legalbench","value":0.7594,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-oss-120b","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":7.85,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"z-ai/glm-4.5","source":"vals-more","metric":"vals_legalbench","value":0.7563,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"z-ai/glm-4.5","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":16.4,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"minimax/minimax-m2.1","source":"vals-more","metric":"vals_legalbench","value":0.7545000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"minimax/minimax-m2.1","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":11.49,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"meta-llama/llama-4-scout","source":"vals-more","metric":"vals_legalbench","value":0.7204,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"meta-llama/llama-4-scout","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":0.39,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/o3-mini","source":"vals-more","metric":"vals_legalbench","value":0.7154,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/o3-mini","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":12.01,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-oss-20b","source":"vals-more","metric":"vals_legalbench","value":0.7084999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-oss-20b","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":7.19,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"google/gemma-2-27b-it","source":"vals-more","metric":"vals_legalbench","value":0.6798000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"google/gemma-2-27b-it","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":0.89,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-3.5-turbo","source":"vals-more","metric":"vals_legalbench","value":0.6437,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-3.5-turbo","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":0.54,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"mistralai/mistral-medium-3.1","source":"vals-more","metric":"vals_legalbench","value":0.6198,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"mistralai/mistral-medium-3.1","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":0.68,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-4.1-nano","source":"vals-more","metric":"vals_legalbench","value":0.6106,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-4.1-nano","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":0.36,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-5-nano","source":"vals-more","metric":"vals_legalbench","value":0.5013000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"openai/gpt-5-nano","source":"vals-more","metric":"vals_legalbench_latency_seconds","value":22.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/legal_bench"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_caselaw","value":0.7931,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":42.81,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"openai/gpt-5.1","source":"vals-more","metric":"vals_caselaw","value":0.7342,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"openai/gpt-5.1","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":23.59,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"openai/gpt-4.1","source":"vals-more","metric":"vals_caselaw","value":0.6988,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"openai/gpt-4.1","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":6.66,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"openai/gpt-5-mini","source":"vals-more","metric":"vals_caselaw","value":0.6849,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"openai/gpt-5-mini","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":42.51,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_caselaw","value":0.6838,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":17.68,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"openai/gpt-5","source":"vals-more","metric":"vals_caselaw","value":0.6645,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"openai/gpt-5","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":123,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_caselaw","value":0.6624,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":25.2,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"openai/gpt-5.2","source":"vals-more","metric":"vals_caselaw","value":0.6602,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"openai/gpt-5.2","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":86.23,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"moonshotai/kimi-k2-thinking","source":"vals-more","metric":"vals_caselaw","value":0.657,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"moonshotai/kimi-k2-thinking","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":91.05,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_caselaw","value":0.6484000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":56.78,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"cohere/command-a","source":"vals-more","metric":"vals_caselaw","value":0.6452,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"cohere/command-a","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":41.55,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_caselaw","value":0.6399,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":36.2,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"google/gemini-2.5-pro","source":"vals-more","metric":"vals_caselaw","value":0.6388,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"google/gemini-2.5-pro","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":44.02,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_caselaw","value":0.6377,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":56.8,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-more","metric":"vals_caselaw","value":0.6259,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":16.82,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-more","metric":"vals_caselaw","value":0.6215999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":25.42,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"anthropic/claude-opus-4.6","source":"vals-more","metric":"vals_caselaw","value":0.6206,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"anthropic/claude-opus-4.6","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":32.27,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"mistralai/mistral-large-2512","source":"vals-more","metric":"vals_caselaw","value":0.6141,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"mistralai/mistral-large-2512","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":40.84,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_caselaw","value":0.612,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":46.09,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_caselaw","value":0.6088,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":21.64,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"openai/gpt-4o-2024-11-20","source":"vals-more","metric":"vals_caselaw","value":0.597,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"openai/gpt-4o-2024-11-20","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":40.87,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"vals-more","metric":"vals_caselaw","value":0.597,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":94.69,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_caselaw","value":0.5938,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":48.44,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_caselaw","value":0.5872999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":241,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"arcee-ai/trinity-large-thinking","source":"vals-more","metric":"vals_caselaw","value":0.5788,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"arcee-ai/trinity-large-thinking","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":14.55,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_caselaw","value":0.5648,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":32.92,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"vals-more","metric":"vals_caselaw","value":0.5595,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":43.54,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"minimax/minimax-m2.1","source":"vals-more","metric":"vals_caselaw","value":0.5584,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"minimax/minimax-m2.1","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":37.36,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_caselaw","value":0.5584,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":261,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"deepseek/deepseek-v3.2","source":"vals-more","metric":"vals_caselaw","value":0.5540999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"deepseek/deepseek-v3.2","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":66.08,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_caselaw","value":0.5498,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":4.64,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"z-ai/glm-4.7","source":"vals-more","metric":"vals_caselaw","value":0.5488000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"z-ai/glm-4.7","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":59.64,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_caselaw","value":0.5445,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":10.66,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"minimax/minimax-m2.5","source":"vals-more","metric":"vals_caselaw","value":0.5347999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"minimax/minimax-m2.5","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":30.88,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"qwen/qwen3.6-27b","source":"vals-more","metric":"vals_caselaw","value":0.5316,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"qwen/qwen3.6-27b","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":42.49,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"google/gemma-4-31b-it","source":"vals-more","metric":"vals_caselaw","value":0.5263,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"google/gemma-4-31b-it","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":28.72,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"openai/gpt-5-nano","source":"vals-more","metric":"vals_caselaw","value":0.5263,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"openai/gpt-5-nano","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":56.48,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"z-ai/glm-5","source":"vals-more","metric":"vals_caselaw","value":0.5252,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"z-ai/glm-5","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":117.98,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_caselaw","value":0.5188,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":7.62,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_caselaw","value":0.5166,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":57.68,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_caselaw","value":0.5155,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":48.96,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_caselaw","value":0.5145000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":43.91,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"openai/gpt-oss-120b","source":"vals-more","metric":"vals_caselaw","value":0.4877,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"openai/gpt-oss-120b","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":68.35,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_caselaw","value":0.4416,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":64.64,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"openai/gpt-oss-20b","source":"vals-more","metric":"vals_caselaw","value":0.4384,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"openai/gpt-oss-20b","source":"vals-more","metric":"vals_caselaw_latency_seconds","value":85.7,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/case_law_v2"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_corpfin","value":0.7319,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":28.57,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_corpfin","value":0.7182999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":52.99,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_corpfin","value":0.7156,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":37.99,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_corpfin","value":0.7129000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":27.82,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_corpfin","value":0.7094,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":30.05,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_corpfin","value":0.6962,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":45.32,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_corpfin","value":0.6857,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":29.2,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_corpfin","value":0.6853,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":36.44,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_corpfin","value":0.6842,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":23.3,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_corpfin","value":0.6826000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":80.78,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_corpfin","value":0.6809999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":24.46,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_corpfin","value":0.6740999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":91.88,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"anthropic/claude-opus-4.6","source":"vals-more","metric":"vals_corpfin","value":0.6701999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"anthropic/claude-opus-4.6","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":20.58,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_corpfin","value":0.6698000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":18.63,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_corpfin","value":0.6674,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":79.59,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_corpfin","value":0.6670999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":20.23,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_corpfin","value":0.6643000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":11.28,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_corpfin","value":0.6616,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":24.26,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_corpfin","value":0.6612,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":24.59,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_corpfin","value":0.6607999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":17.75,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-5.2","source":"vals-more","metric":"vals_corpfin","value":0.6589,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-5.2","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":26.04,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_corpfin","value":0.6585,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":46.65,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"vals-more","metric":"vals_corpfin","value":0.6546,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":15.02,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_corpfin","value":0.6542,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":32.85,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_corpfin","value":0.6531,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":7.72,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_corpfin","value":0.6531,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":18.48,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"vals-more","metric":"vals_corpfin","value":0.6531,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":156,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_corpfin","value":0.6527,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":82.34,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-more","metric":"vals_corpfin","value":0.6507,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":17.73,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_corpfin","value":0.6469,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":8.7,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_corpfin","value":0.6448999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":25.39,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_corpfin","value":0.6445000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":68.17,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_corpfin","value":0.6437999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":15.94,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_corpfin","value":0.6422,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":16.97,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-5.1","source":"vals-more","metric":"vals_corpfin","value":0.6383,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-5.1","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":35.29,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_corpfin","value":0.6371,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":19.93,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_corpfin","value":0.6367,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":9.67,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"vals-more","metric":"vals_corpfin","value":0.6356,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":35.2,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_corpfin","value":0.6333,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":6.33,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-4.1","source":"vals-more","metric":"vals_corpfin","value":0.6305,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-4.1","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":10.14,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"z-ai/glm-5","source":"vals-more","metric":"vals_corpfin","value":0.629,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"z-ai/glm-5","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":68.58,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"qwen/qwen3.6-27b","source":"vals-more","metric":"vals_corpfin","value":0.6231,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"qwen/qwen3.6-27b","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":62.76,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-more","metric":"vals_corpfin","value":0.6197,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":20.54,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_corpfin","value":0.6193,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":12.45,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_corpfin","value":0.6193,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":35.84,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_corpfin","value":0.6185,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":16.48,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_corpfin","value":0.6142,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":18.9,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_corpfin","value":0.6138,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":79.33,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_corpfin","value":0.6119,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":9.4,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_corpfin","value":0.6119,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":10.97,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-5","source":"vals-more","metric":"vals_corpfin","value":0.6107,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-5","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":161,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"mistralai/mistral-large-2512","source":"vals-more","metric":"vals_corpfin","value":0.6103000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"mistralai/mistral-large-2512","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":48.84,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"z-ai/glm-4.5","source":"vals-more","metric":"vals_corpfin","value":0.6096,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"z-ai/glm-4.5","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":95.24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_corpfin","value":0.6092,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":52.3,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"google/gemini-2.5-pro","source":"vals-more","metric":"vals_corpfin","value":0.608,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"google/gemini-2.5-pro","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":27.43,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_corpfin","value":0.6068,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":3.84,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_corpfin","value":0.6061,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":14.24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"moonshotai/kimi-k2-thinking","source":"vals-more","metric":"vals_corpfin","value":0.6057,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"moonshotai/kimi-k2-thinking","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":93.3,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-5-mini","source":"vals-more","metric":"vals_corpfin","value":0.6018,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-5-mini","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":73.79,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_corpfin","value":0.5991,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":17.63,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/o3","source":"vals-more","metric":"vals_corpfin","value":0.5971,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/o3","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":19.15,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"minimax/minimax-m2.5","source":"vals-more","metric":"vals_corpfin","value":0.596,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"minimax/minimax-m2.5","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":16.6,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_corpfin","value":0.5936,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":4.03,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/o4-mini","source":"vals-more","metric":"vals_corpfin","value":0.5897,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/o4-mini","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":17.53,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"minimax/minimax-m2.1","source":"vals-more","metric":"vals_corpfin","value":0.589,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"minimax/minimax-m2.1","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":21.97,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_corpfin","value":0.5878,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":43.7,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-oss-120b","source":"vals-more","metric":"vals_corpfin","value":0.5824,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-oss-120b","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":42.72,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-4.1-mini","source":"vals-more","metric":"vals_corpfin","value":0.5793,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-4.1-mini","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":6.44,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"google/gemini-2.5-flash-lite","source":"vals-more","metric":"vals_corpfin","value":0.5758,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"google/gemini-2.5-flash-lite","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":54.23,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"z-ai/glm-4.6","source":"vals-more","metric":"vals_corpfin","value":0.5684,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"z-ai/glm-4.6","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":78.06,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"vals-more","metric":"vals_corpfin","value":0.5474,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":36.73,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"arcee-ai/trinity-large-thinking","source":"vals-more","metric":"vals_corpfin","value":0.5466,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"arcee-ai/trinity-large-thinking","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":12.48,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"vals-more","metric":"vals_corpfin","value":0.5423,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":38.79,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-oss-20b","source":"vals-more","metric":"vals_corpfin","value":0.5315,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-oss-20b","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":33.97,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"deepseek/deepseek-v3.2","source":"vals-more","metric":"vals_corpfin","value":0.5097,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"deepseek/deepseek-v3.2","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":99.48,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"mistralai/mistral-medium-3.1","source":"vals-more","metric":"vals_corpfin","value":0.5074000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"mistralai/mistral-medium-3.1","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":30.35,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"moonshotai/kimi-k2","source":"vals-more","metric":"vals_corpfin","value":0.5039,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"moonshotai/kimi-k2","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":40.89,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"meta-llama/llama-4-maverick","source":"vals-more","metric":"vals_corpfin","value":0.49729999999999996,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"meta-llama/llama-4-maverick","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":4.72,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"meta-llama/llama-4-scout","source":"vals-more","metric":"vals_corpfin","value":0.4678,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"meta-llama/llama-4-scout","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":9.7,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"z-ai/glm-4.7","source":"vals-more","metric":"vals_corpfin","value":0.4639,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"z-ai/glm-4.7","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":66.1,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"cohere/command-a","source":"vals-more","metric":"vals_corpfin","value":0.4596,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"cohere/command-a","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":14.15,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-4o-2024-11-20","source":"vals-more","metric":"vals_corpfin","value":0.4592,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-4o-2024-11-20","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":6.46,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-4o-mini","source":"vals-more","metric":"vals_corpfin","value":0.4545,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-4o-mini","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":0.04,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/o3-mini","source":"vals-more","metric":"vals_corpfin","value":0.45299999999999996,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/o3-mini","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":31.05,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-4.1-nano","source":"vals-more","metric":"vals_corpfin","value":0.4208,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-4.1-nano","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":4.95,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-4o-2024-08-06","source":"vals-more","metric":"vals_corpfin","value":0.3943,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"openai/gpt-4o-2024-08-06","source":"vals-more","metric":"vals_corpfin_latency_seconds","value":0.05,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/corp_fin_v2"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_taxeval","value":0.8038,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":48.31,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_taxeval","value":0.7972,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":32.82,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_taxeval","value":0.7711,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":128,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_taxeval","value":0.7694,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":56.87,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_taxeval","value":0.7617,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":37.28,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_taxeval","value":0.7617,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":76.52,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"anthropic/claude-opus-4.6","source":"vals-more","metric":"vals_taxeval","value":0.7595999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"anthropic/claude-opus-4.6","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":79.25,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_taxeval","value":0.7595999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":85.56,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-5.2","source":"vals-more","metric":"vals_taxeval","value":0.7576,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-5.2","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":60.48,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_taxeval","value":0.7572,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":145,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_taxeval","value":0.7563,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":70.33,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_taxeval","value":0.7563,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":202,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_taxeval","value":0.7559,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":53.06,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_taxeval","value":0.7555,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":266,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_taxeval","value":0.7551000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":242,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_taxeval","value":0.7531,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":57.68,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_taxeval","value":0.7531,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":198,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_taxeval","value":0.7526999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":62.07,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-5-mini","source":"vals-more","metric":"vals_taxeval","value":0.7522,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-5-mini","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":37.43,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_taxeval","value":0.7514,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":58.34,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-4.1","source":"vals-more","metric":"vals_taxeval","value":0.7506,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-4.1","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":7.89,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_taxeval","value":0.7498,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":95.83,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_taxeval","value":0.7486,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":12.34,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-5.1","source":"vals-more","metric":"vals_taxeval","value":0.7486,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-5.1","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":44.18,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-more","metric":"vals_taxeval","value":0.7486,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":47.45,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/o4-mini","source":"vals-more","metric":"vals_taxeval","value":0.7478,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/o4-mini","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":15.45,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_taxeval","value":0.7478,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":62.03,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_taxeval","value":0.7473000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":7.83,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_taxeval","value":0.7473000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":70.63,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_taxeval","value":0.7465,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":267,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/o3","source":"vals-more","metric":"vals_taxeval","value":0.7456999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/o3","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":24.02,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-4o-2024-11-20","source":"vals-more","metric":"vals_taxeval","value":0.7453,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-4o-2024-11-20","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":5.86,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_taxeval","value":0.7445,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":8.76,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_taxeval","value":0.7437,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":19.69,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/o1","source":"vals-more","metric":"vals_taxeval","value":0.7428,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/o1","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":19.48,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_taxeval","value":0.742,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":90.46,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_taxeval","value":0.7412000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":13.39,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_taxeval","value":0.7395999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":78.72,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_taxeval","value":0.7387999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":12,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_taxeval","value":0.7379000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":62.83,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"anthropic/claude-opus-4.1","source":"vals-more","metric":"vals_taxeval","value":0.7367,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"anthropic/claude-opus-4.1","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":26.64,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-5","source":"vals-more","metric":"vals_taxeval","value":0.7339,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-5","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":78.67,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_taxeval","value":0.7334,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":64.94,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-more","metric":"vals_taxeval","value":0.733,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":48.39,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"vals-more","metric":"vals_taxeval","value":0.731,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":36.48,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"mistralai/mistral-large-2512","source":"vals-more","metric":"vals_taxeval","value":0.7306,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"mistralai/mistral-large-2512","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":29.53,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_taxeval","value":0.7306,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":226,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_taxeval","value":0.7288,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":41.93,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_taxeval","value":0.7273000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":94.04,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_taxeval","value":0.7261,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":8.81,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"z-ai/glm-4.5","source":"vals-more","metric":"vals_taxeval","value":0.7240000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"z-ai/glm-4.5","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":129,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_taxeval","value":0.7236,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":98.32,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"vals-more","metric":"vals_taxeval","value":0.7216,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":73,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_taxeval","value":0.7208,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":190,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-4.1-mini","source":"vals-more","metric":"vals_taxeval","value":0.7191,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-4.1-mini","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":5.92,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_taxeval","value":0.7182999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":26.3,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_taxeval","value":0.7179000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":7.64,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"moonshotai/kimi-k2-thinking","source":"vals-more","metric":"vals_taxeval","value":0.7171,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"moonshotai/kimi-k2-thinking","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":61.41,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_taxeval","value":0.7167,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":195,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-oss-120b","source":"vals-more","metric":"vals_taxeval","value":0.7159,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-oss-120b","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":47.66,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"qwen/qwen3.6-27b","source":"vals-more","metric":"vals_taxeval","value":0.7126,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"qwen/qwen3.6-27b","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":148,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_taxeval","value":0.7121999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":44.58,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_taxeval","value":0.7119,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":84.07,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-4o-2024-08-06","source":"vals-more","metric":"vals_taxeval","value":0.7114,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-4o-2024-08-06","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":9.54,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"vals-more","metric":"vals_taxeval","value":0.711,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":34.01,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_taxeval","value":0.711,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":47.57,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_taxeval","value":0.7084999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":94.49,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_taxeval","value":0.7081000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":392,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_taxeval","value":0.7069,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":72.2,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_taxeval","value":0.7065,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":7.54,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"mistralai/mistral-medium-3.1","source":"vals-more","metric":"vals_taxeval","value":0.7031999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"mistralai/mistral-medium-3.1","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":11.05,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"moonshotai/kimi-k2","source":"vals-more","metric":"vals_taxeval","value":0.7020000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"moonshotai/kimi-k2","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":12.83,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"z-ai/glm-5","source":"vals-more","metric":"vals_taxeval","value":0.7003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"z-ai/glm-5","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":149,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/o3-mini","source":"vals-more","metric":"vals_taxeval","value":0.6942,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/o3-mini","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":74.31,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"z-ai/glm-4.7","source":"vals-more","metric":"vals_taxeval","value":0.6877,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"z-ai/glm-4.7","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":187,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"minimax/minimax-m2.5","source":"vals-more","metric":"vals_taxeval","value":0.6815000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"minimax/minimax-m2.5","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":73.24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"deepseek/deepseek-v3.2","source":"vals-more","metric":"vals_taxeval","value":0.6815000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"deepseek/deepseek-v3.2","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":98.92,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_taxeval","value":0.6799,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":102.39,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_taxeval","value":0.6754000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":47.52,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_taxeval","value":0.6742,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":15.9,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-5-nano","source":"vals-more","metric":"vals_taxeval","value":0.6738,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-5-nano","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":69.94,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"meta-llama/llama-4-maverick","source":"vals-more","metric":"vals_taxeval","value":0.6656,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"meta-llama/llama-4-maverick","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":25.14,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_taxeval","value":0.6656,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":28.69,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"minimax/minimax-m2.1","source":"vals-more","metric":"vals_taxeval","value":0.6635,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"minimax/minimax-m2.1","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":113.26,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"z-ai/glm-4.6","source":"vals-more","metric":"vals_taxeval","value":0.6623,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"z-ai/glm-4.6","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":64.15,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"google/gemini-2.5-flash-lite","source":"vals-more","metric":"vals_taxeval","value":0.6623,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"google/gemini-2.5-flash-lite","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":3.6,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"mistralai/mistral-large","source":"vals-more","metric":"vals_taxeval","value":0.6378,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"mistralai/mistral-large","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":12.02,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-oss-20b","source":"vals-more","metric":"vals_taxeval","value":0.637,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-oss-20b","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":49,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"cohere/command-a","source":"vals-more","metric":"vals_taxeval","value":0.6137,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"cohere/command-a","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":11.21,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-4.1-nano","source":"vals-more","metric":"vals_taxeval","value":0.6075,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-4.1-nano","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":3,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-4o-mini","source":"vals-more","metric":"vals_taxeval","value":0.6054999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"openai/gpt-4o-mini","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":8.9,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"meta-llama/llama-4-scout","source":"vals-more","metric":"vals_taxeval","value":0.5519,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"meta-llama/llama-4-scout","source":"vals-more","metric":"vals_taxeval_latency_seconds","value":7.04,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/tax_eval_v2"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_mortgagetax","value":0.7206,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":7.98,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_mortgagetax","value":0.7079000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":14.98,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_mortgagetax","value":0.7027,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":16.1,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_mortgagetax","value":0.7003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":28.67,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_mortgagetax","value":0.6990999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":20.81,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_mortgagetax","value":0.6940000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":23.62,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_mortgagetax","value":0.6892,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":16.1,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"google/gemini-2.5-pro","source":"vals-more","metric":"vals_mortgagetax","value":0.6892,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"google/gemini-2.5-pro","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":24.01,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_mortgagetax","value":0.6876000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":28.24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_mortgagetax","value":0.6872,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":12.84,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_mortgagetax","value":0.6868000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":4.88,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-more","metric":"vals_mortgagetax","value":0.6868000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":10.53,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"anthropic/claude-opus-4.6","source":"vals-more","metric":"vals_mortgagetax","value":0.6851999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"anthropic/claude-opus-4.6","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":27.16,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_mortgagetax","value":0.6836,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":26.76,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_mortgagetax","value":0.6831999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":45,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"qwen/qwen3.6-27b","source":"vals-more","metric":"vals_mortgagetax","value":0.6828,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"qwen/qwen3.6-27b","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":42.07,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_mortgagetax","value":0.6812,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":11.43,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_mortgagetax","value":0.6804000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":5.37,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_mortgagetax","value":0.6797,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":78.18,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_mortgagetax","value":0.6773,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":29.74,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_mortgagetax","value":0.6761,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":9.24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"vals-more","metric":"vals_mortgagetax","value":0.6737000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":36.82,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_mortgagetax","value":0.6733,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":6.32,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_mortgagetax","value":0.6729,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":22.84,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_mortgagetax","value":0.6729,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":12.62,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-5.2","source":"vals-more","metric":"vals_mortgagetax","value":0.6713,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-5.2","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":70.67,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-5-mini","source":"vals-more","metric":"vals_mortgagetax","value":0.6689,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-5-mini","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":24.86,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_mortgagetax","value":0.6665000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":4.11,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_mortgagetax","value":0.6653,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":79.79,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_mortgagetax","value":0.6634,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":78.94,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"qwen/qwen3.7-plus","source":"vals-more","metric":"vals_mortgagetax","value":0.6618,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"qwen/qwen3.7-plus","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":60.55,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_mortgagetax","value":0.6614,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":24.82,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-4.1","source":"vals-more","metric":"vals_mortgagetax","value":0.6594,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-4.1","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":5.03,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_mortgagetax","value":0.6581999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":109.76,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/o3","source":"vals-more","metric":"vals_mortgagetax","value":0.657,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/o3","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":21.22,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-4.1-mini","source":"vals-more","metric":"vals_mortgagetax","value":0.655,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-4.1-mini","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":4.6,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-5","source":"vals-more","metric":"vals_mortgagetax","value":0.6545000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-5","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":62.83,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_mortgagetax","value":0.6542,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":44.62,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_mortgagetax","value":0.6534,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":14.79,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_mortgagetax","value":0.6494,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":79.95,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/o4-mini","source":"vals-more","metric":"vals_mortgagetax","value":0.6483,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/o4-mini","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":13,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_mortgagetax","value":0.6419,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":8.55,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_mortgagetax","value":0.6399,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":47.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-more","metric":"vals_mortgagetax","value":0.6399,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":47.62,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_mortgagetax","value":0.6399,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":69.11,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_mortgagetax","value":0.6351,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":126,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_mortgagetax","value":0.6228,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":112.21,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_mortgagetax","value":0.6215999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":29.79,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_mortgagetax","value":0.618,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":117.46,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"google/gemma-4-31b-it","source":"vals-more","metric":"vals_mortgagetax","value":0.6137,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"google/gemma-4-31b-it","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":41.93,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-5.1","source":"vals-more","metric":"vals_mortgagetax","value":0.6137,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-5.1","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":46.25,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"anthropic/claude-opus-4.1","source":"vals-more","metric":"vals_mortgagetax","value":0.6109,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"anthropic/claude-opus-4.1","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":10.06,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-4o-2024-08-06","source":"vals-more","metric":"vals_mortgagetax","value":0.6097,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-4o-2024-08-06","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":7.36,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"vals-more","metric":"vals_mortgagetax","value":0.6077,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":62.08,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_mortgagetax","value":0.5926,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":32.94,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_mortgagetax","value":0.591,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":14.53,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"meta-llama/llama-4-maverick","source":"vals-more","metric":"vals_mortgagetax","value":0.5851,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"meta-llama/llama-4-maverick","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":2.72,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"meta-llama/llama-4-scout","source":"vals-more","metric":"vals_mortgagetax","value":0.5775,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"meta-llama/llama-4-scout","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":2.43,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"google/gemini-2.5-flash-lite","source":"vals-more","metric":"vals_mortgagetax","value":0.5755,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"google/gemini-2.5-flash-lite","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":28.21,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-4o-2024-11-20","source":"vals-more","metric":"vals_mortgagetax","value":0.5743,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-4o-2024-11-20","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":5.98,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-4o-mini","source":"vals-more","metric":"vals_mortgagetax","value":0.5449,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-4o-mini","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":6.06,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-5-nano","source":"vals-more","metric":"vals_mortgagetax","value":0.5362,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-5-nano","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":33.36,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-4.1-nano","source":"vals-more","metric":"vals_mortgagetax","value":0.5282,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/gpt-4.1-nano","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":3.86,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"mistralai/mistral-large-2512","source":"vals-more","metric":"vals_mortgagetax","value":0.5211,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"mistralai/mistral-large-2512","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":9.29,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_mortgagetax","value":0.4825,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":443,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_mortgagetax","value":0.4535,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":11.12,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"mistralai/mistral-medium-3.1","source":"vals-more","metric":"vals_mortgagetax","value":0.36450000000000005,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"mistralai/mistral-medium-3.1","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":7.14,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_mortgagetax","value":0.2889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_mortgagetax_latency_seconds","value":68.43,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/mortgage_tax"},{"modelId":"openai/o1","source":"vals-more","metric":"vals_medqa","value":0.9652,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/o1","source":"vals-more","metric":"vals_medqa_latency_seconds","value":11.15,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/gpt-5.1","source":"vals-more","metric":"vals_medqa","value":0.9638,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/gpt-5.1","source":"vals-more","metric":"vals_medqa_latency_seconds","value":12.29,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_medqa","value":0.9637,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_medqa_latency_seconds","value":38.67,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/gpt-5","source":"vals-more","metric":"vals_medqa","value":0.9632,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/gpt-5","source":"vals-more","metric":"vals_medqa_latency_seconds","value":35.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_medqa","value":0.9609000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_medqa_latency_seconds","value":22.78,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/o3","source":"vals-more","metric":"vals_medqa","value":0.9606,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/o3","source":"vals-more","metric":"vals_medqa_latency_seconds","value":8.51,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/gpt-5-mini","source":"vals-more","metric":"vals_medqa","value":0.9606,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/gpt-5-mini","source":"vals-more","metric":"vals_medqa_latency_seconds","value":16.25,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/o4-mini","source":"vals-more","metric":"vals_medqa","value":0.9601999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/o4-mini","source":"vals-more","metric":"vals_medqa_latency_seconds","value":6.6,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-more","metric":"vals_medqa","value":0.9588,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-more","metric":"vals_medqa_latency_seconds","value":31.63,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_medqa","value":0.9581000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_medqa_latency_seconds","value":26.32,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"anthropic/claude-opus-4.6","source":"vals-more","metric":"vals_medqa","value":0.9541,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"anthropic/claude-opus-4.6","source":"vals-more","metric":"vals_medqa_latency_seconds","value":30.09,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"vals-more","metric":"vals_medqa","value":0.9521,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"qwen/qwen3.5-plus-20260420","source":"vals-more","metric":"vals_medqa_latency_seconds","value":52.36,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/o3-mini","source":"vals-more","metric":"vals_medqa","value":0.9483,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/o3-mini","source":"vals-more","metric":"vals_medqa_latency_seconds","value":8.39,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-more","metric":"vals_medqa","value":0.9470999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-more","metric":"vals_medqa_latency_seconds","value":35.78,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_medqa","value":0.9455,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_medqa_latency_seconds","value":12.22,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_medqa","value":0.9437000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_medqa_latency_seconds","value":41.63,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"z-ai/glm-5","source":"vals-more","metric":"vals_medqa","value":0.9427,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"z-ai/glm-5","source":"vals-more","metric":"vals_medqa_latency_seconds","value":81.08,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/gpt-5.2","source":"vals-more","metric":"vals_medqa","value":0.9412999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/gpt-5.2","source":"vals-more","metric":"vals_medqa_latency_seconds","value":19.48,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"deepseek/deepseek-v3.2","source":"vals-more","metric":"vals_medqa","value":0.9392,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"deepseek/deepseek-v3.2","source":"vals-more","metric":"vals_medqa_latency_seconds","value":53.69,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"z-ai/glm-4.7","source":"vals-more","metric":"vals_medqa","value":0.9373999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"z-ai/glm-4.7","source":"vals-more","metric":"vals_medqa_latency_seconds","value":66.01,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"anthropic/claude-opus-4.1","source":"vals-more","metric":"vals_medqa","value":0.9359000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"anthropic/claude-opus-4.1","source":"vals-more","metric":"vals_medqa_latency_seconds","value":23.61,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/gpt-5-nano","source":"vals-more","metric":"vals_medqa","value":0.9326000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/gpt-5-nano","source":"vals-more","metric":"vals_medqa_latency_seconds","value":20.46,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"moonshotai/kimi-k2-thinking","source":"vals-more","metric":"vals_medqa","value":0.9259000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"moonshotai/kimi-k2-thinking","source":"vals-more","metric":"vals_medqa_latency_seconds","value":225,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"minimax/minimax-m2.5","source":"vals-more","metric":"vals_medqa","value":0.9253,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"minimax/minimax-m2.5","source":"vals-more","metric":"vals_medqa_latency_seconds","value":33.54,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"z-ai/glm-4.6","source":"vals-more","metric":"vals_medqa","value":0.9222,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"z-ai/glm-4.6","source":"vals-more","metric":"vals_medqa_latency_seconds","value":28.73,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_medqa","value":0.9206,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_medqa_latency_seconds","value":35.12,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/gpt-oss-120b","source":"vals-more","metric":"vals_medqa","value":0.9136,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/gpt-oss-120b","source":"vals-more","metric":"vals_medqa_latency_seconds","value":12.38,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/gpt-4.1","source":"vals-more","metric":"vals_medqa","value":0.9118,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/gpt-4.1","source":"vals-more","metric":"vals_medqa_latency_seconds","value":3.08,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"minimax/minimax-m2.1","source":"vals-more","metric":"vals_medqa","value":0.9116,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"minimax/minimax-m2.1","source":"vals-more","metric":"vals_medqa_latency_seconds","value":35.94,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"z-ai/glm-4.5","source":"vals-more","metric":"vals_medqa","value":0.8996999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"z-ai/glm-4.5","source":"vals-more","metric":"vals_medqa_latency_seconds","value":59.61,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"google/gemini-2.5-flash-lite","source":"vals-more","metric":"vals_medqa","value":0.8887,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"google/gemini-2.5-flash-lite","source":"vals-more","metric":"vals_medqa_latency_seconds","value":14.82,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/gpt-4o-2024-08-06","source":"vals-more","metric":"vals_medqa","value":0.8815999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/gpt-4o-2024-08-06","source":"vals-more","metric":"vals_medqa_latency_seconds","value":3.39,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/gpt-4.1-mini","source":"vals-more","metric":"vals_medqa","value":0.8462999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/gpt-4.1-mini","source":"vals-more","metric":"vals_medqa_latency_seconds","value":1.86,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"moonshotai/kimi-k2","source":"vals-more","metric":"vals_medqa","value":0.8397,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"moonshotai/kimi-k2","source":"vals-more","metric":"vals_medqa_latency_seconds","value":10.98,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/gpt-oss-20b","source":"vals-more","metric":"vals_medqa","value":0.8288,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/gpt-oss-20b","source":"vals-more","metric":"vals_medqa_latency_seconds","value":25.35,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"mistralai/mistral-large-2512","source":"vals-more","metric":"vals_medqa","value":0.8223,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"mistralai/mistral-large-2512","source":"vals-more","metric":"vals_medqa_latency_seconds","value":17.31,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"vals-more","metric":"vals_medqa","value":0.82,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"vals-more","metric":"vals_medqa_latency_seconds","value":12.88,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/gpt-4-turbo","source":"vals-more","metric":"vals_medqa","value":0.8199,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/gpt-4-turbo","source":"vals-more","metric":"vals_medqa_latency_seconds","value":8.41,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"cohere/command-a","source":"vals-more","metric":"vals_medqa","value":0.8055,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"cohere/command-a","source":"vals-more","metric":"vals_medqa_latency_seconds","value":2.91,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_medqa","value":0.7957,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_medqa_latency_seconds","value":23.91,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"mistralai/mistral-medium-3.1","source":"vals-more","metric":"vals_medqa","value":0.7823,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"mistralai/mistral-medium-3.1","source":"vals-more","metric":"vals_medqa_latency_seconds","value":7.34,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"mistralai/mistral-large","source":"vals-more","metric":"vals_medqa","value":0.7622,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"mistralai/mistral-large","source":"vals-more","metric":"vals_medqa_latency_seconds","value":4.86,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/gpt-4o-mini","source":"vals-more","metric":"vals_medqa","value":0.7243999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/gpt-4o-mini","source":"vals-more","metric":"vals_medqa_latency_seconds","value":2.32,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/gpt-4.1-nano","source":"vals-more","metric":"vals_medqa","value":0.6822,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/gpt-4.1-nano","source":"vals-more","metric":"vals_medqa_latency_seconds","value":1.42,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/gpt-3.5-turbo","source":"vals-more","metric":"vals_medqa","value":0.5847,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"openai/gpt-3.5-turbo","source":"vals-more","metric":"vals_medqa_latency_seconds","value":1.59,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"meta-llama/llama-4-scout","source":"vals-more","metric":"vals_medqa","value":0.509,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"meta-llama/llama-4-scout","source":"vals-more","metric":"vals_medqa_latency_seconds","value":4.8,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"meta-llama/llama-4-maverick","source":"vals-more","metric":"vals_medqa","value":0.433,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"meta-llama/llama-4-maverick","source":"vals-more","metric":"vals_medqa_latency_seconds","value":7.75,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medqa"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_medcode","value":0.6357,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_medcode_latency_seconds","value":24.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_medcode","value":0.5906,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_medcode_latency_seconds","value":38.52,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_medcode","value":0.588,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_medcode_latency_seconds","value":79.53,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_medcode","value":0.5607,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_medcode_latency_seconds","value":91.44,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_medcode","value":0.5592,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_medcode_latency_seconds","value":44.15,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_medcode","value":0.5583,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_medcode_latency_seconds","value":25.29,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_medcode","value":0.5486,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_medcode_latency_seconds","value":54.25,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_medcode","value":0.5351,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_medcode_latency_seconds","value":215,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_medcode","value":0.5339,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_medcode_latency_seconds","value":9.16,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_medcode","value":0.5322,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_medcode_latency_seconds","value":105.92,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_medcode","value":0.5315,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_medcode_latency_seconds","value":16.68,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_medcode","value":0.5292,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_medcode_latency_seconds","value":239,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"openai/gpt-5.1","source":"vals-more","metric":"vals_medcode","value":0.5273,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"openai/gpt-5.1","source":"vals-more","metric":"vals_medcode_latency_seconds","value":54.55,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_medcode","value":0.5154,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_medcode_latency_seconds","value":226,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"google/gemini-2.5-pro","source":"vals-more","metric":"vals_medcode","value":0.5059,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"google/gemini-2.5-pro","source":"vals-more","metric":"vals_medcode_latency_seconds","value":27.41,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_medcode","value":0.498,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_medcode_latency_seconds","value":247,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"openai/gpt-5.2","source":"vals-more","metric":"vals_medcode","value":0.4975,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"openai/gpt-5.2","source":"vals-more","metric":"vals_medcode_latency_seconds","value":157,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"openai/gpt-5","source":"vals-more","metric":"vals_medcode","value":0.4963,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"openai/gpt-5","source":"vals-more","metric":"vals_medcode_latency_seconds","value":58.27,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_medcode","value":0.4955,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_medcode_latency_seconds","value":213,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_medcode","value":0.4936,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_medcode_latency_seconds","value":36.99,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_medcode","value":0.4935,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_medcode_latency_seconds","value":60.17,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-more","metric":"vals_medcode","value":0.4916,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-more","metric":"vals_medcode_latency_seconds","value":60.84,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"anthropic/claude-opus-4.6","source":"vals-more","metric":"vals_medcode","value":0.4913,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"anthropic/claude-opus-4.6","source":"vals-more","metric":"vals_medcode_latency_seconds","value":156,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_medcode","value":0.491,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_medcode_latency_seconds","value":160,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_medcode","value":0.48840000000000006,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_medcode_latency_seconds","value":115.34,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_medcode","value":0.4849,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_medcode_latency_seconds","value":102.86,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_medcode","value":0.4813,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_medcode_latency_seconds","value":42.89,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_medcode","value":0.47600000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_medcode_latency_seconds","value":8.55,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_medcode","value":0.4754,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_medcode_latency_seconds","value":135,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"openai/o3","source":"vals-more","metric":"vals_medcode","value":0.4729,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"openai/o3","source":"vals-more","metric":"vals_medcode_latency_seconds","value":17.68,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"anthropic/claude-opus-4.1","source":"vals-more","metric":"vals_medcode","value":0.47229999999999994,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"anthropic/claude-opus-4.1","source":"vals-more","metric":"vals_medcode_latency_seconds","value":33.26,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_medcode","value":0.4707,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_medcode_latency_seconds","value":62.71,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_medcode","value":0.4629,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_medcode_latency_seconds","value":63.12,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_medcode","value":0.4497,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_medcode_latency_seconds","value":177,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_medcode","value":0.4471,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_medcode_latency_seconds","value":127,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_medcode","value":0.44689999999999996,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_medcode_latency_seconds","value":108.77,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-more","metric":"vals_medcode","value":0.4413,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-more","metric":"vals_medcode_latency_seconds","value":74.33,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_medcode","value":0.4397,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_medcode_latency_seconds","value":96.59,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_medcode","value":0.4349,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_medcode_latency_seconds","value":6.02,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_medcode","value":0.4341,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_medcode_latency_seconds","value":18.41,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_medcode","value":0.4329,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_medcode_latency_seconds","value":59.64,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_medcode","value":0.4325,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_medcode_latency_seconds","value":399,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"openai/gpt-5-mini","source":"vals-more","metric":"vals_medcode","value":0.4305,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"openai/gpt-5-mini","source":"vals-more","metric":"vals_medcode_latency_seconds","value":28.17,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_medcode","value":0.4286,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_medcode_latency_seconds","value":169,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_medcode","value":0.42469999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_medcode_latency_seconds","value":181,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_medcode","value":0.4239,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_medcode_latency_seconds","value":81.28,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_medcode","value":0.41600000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_medcode_latency_seconds","value":77.58,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_medcode","value":0.41409999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_medcode_latency_seconds","value":127,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_medcode","value":0.4129,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_medcode_latency_seconds","value":187,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_medcode","value":0.4119,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_medcode_latency_seconds","value":167,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_medcode","value":0.4117,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_medcode_latency_seconds","value":35.13,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_medcode","value":0.4106,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_medcode_latency_seconds","value":93.37,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_medcode","value":0.4103,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_medcode_latency_seconds","value":8.04,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_medcode","value":0.4077,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_medcode_latency_seconds","value":95.27,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_medcode","value":0.4069,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_medcode_latency_seconds","value":68.68,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_medcode","value":0.4067,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_medcode_latency_seconds","value":378,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_medcode","value":0.4045,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_medcode_latency_seconds","value":383,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"google/gemini-2.5-flash","source":"vals-more","metric":"vals_medcode","value":0.4036,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"google/gemini-2.5-flash","source":"vals-more","metric":"vals_medcode_latency_seconds","value":22.83,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_medcode","value":0.4014,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_medcode_latency_seconds","value":305,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_medcode","value":0.3932,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_medcode_latency_seconds","value":75.45,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_medcode","value":0.3875,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_medcode_latency_seconds","value":28.75,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"vals-more","metric":"vals_medcode","value":0.3862,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"vals-more","metric":"vals_medcode_latency_seconds","value":18.68,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_medcode","value":0.3807,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_medcode_latency_seconds","value":43.92,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_medcode","value":0.3789,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_medcode_latency_seconds","value":191,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_medcode","value":0.3689,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_medcode_latency_seconds","value":56.22,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"meta-llama/llama-4-maverick","source":"vals-more","metric":"vals_medcode","value":0.3651,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"meta-llama/llama-4-maverick","source":"vals-more","metric":"vals_medcode_latency_seconds","value":21.24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_medcode","value":0.3444,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_medcode_latency_seconds","value":30.25,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"google/gemini-2.5-flash-lite","source":"vals-more","metric":"vals_medcode","value":0.3419,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"google/gemini-2.5-flash-lite","source":"vals-more","metric":"vals_medcode_latency_seconds","value":10.49,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"minimax/minimax-m2.1","source":"vals-more","metric":"vals_medcode","value":0.3408,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"minimax/minimax-m2.1","source":"vals-more","metric":"vals_medcode_latency_seconds","value":19.55,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"openai/o4-mini","source":"vals-more","metric":"vals_medcode","value":0.3379,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"openai/o4-mini","source":"vals-more","metric":"vals_medcode_latency_seconds","value":21.06,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_medcode","value":0.3375,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_medcode_latency_seconds","value":34.88,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"vals-more","metric":"vals_medcode","value":0.33,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"vals-more","metric":"vals_medcode_latency_seconds","value":63.07,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"z-ai/glm-4.7","source":"vals-more","metric":"vals_medcode","value":0.32770000000000005,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"z-ai/glm-4.7","source":"vals-more","metric":"vals_medcode_latency_seconds","value":123,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_medcode","value":0.3268,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_medcode_latency_seconds","value":34.29,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_medcode","value":0.3248,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_medcode_latency_seconds","value":38.45,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_medcode","value":0.32270000000000004,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_medcode_latency_seconds","value":9.65,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_medcode","value":0.32159999999999994,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_medcode_latency_seconds","value":16.55,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_medcode","value":0.3189,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_medcode_latency_seconds","value":17.7,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_medcode","value":0.31329999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_medcode_latency_seconds","value":7.93,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"openai/gpt-5-nano","source":"vals-more","metric":"vals_medcode","value":0.3044,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"openai/gpt-5-nano","source":"vals-more","metric":"vals_medcode_latency_seconds","value":29.74,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_medcode","value":0.287,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_medcode_latency_seconds","value":89.38,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"meta-llama/llama-4-scout","source":"vals-more","metric":"vals_medcode","value":0.23309999999999997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"meta-llama/llama-4-scout","source":"vals-more","metric":"vals_medcode_latency_seconds","value":10.74,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"cohere/command-a","source":"vals-more","metric":"vals_medcode","value":0.1972,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"cohere/command-a","source":"vals-more","metric":"vals_medcode_latency_seconds","value":103.75,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medcode"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_medscribe","value":0.9143000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"anthropic/claude-opus-5.5","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":442,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_medscribe","value":0.9129,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"anthropic/claude-fable-5.1","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":188,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_medscribe","value":0.9109999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"anthropic/claude-sonnet-5.5","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":307,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_medscribe","value":0.9098,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":76.56,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_medscribe","value":0.9006000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":61.46,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_medscribe","value":0.8954000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"anthropic/claude-haiku-5.5","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":323,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_medscribe","value":0.8937999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"x-ai/grok-4.7","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":153,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_medscribe","value":0.8894,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"z-ai/glm-5.3-flash","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":86.98,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_medscribe","value":0.8889,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":63.34,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_medscribe","value":0.8881,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"z-ai/glm-5.3","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":122,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_medscribe","value":0.8852,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":119.47,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_medscribe","value":0.8831,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":173,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"openai/gpt-5.1","source":"vals-more","metric":"vals_medscribe","value":0.8809,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"openai/gpt-5.1","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":77.98,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_medscribe","value":0.8805,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":38.24,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_medscribe","value":0.8791,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"openai/gpt-6-astra","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":154,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_medscribe","value":0.8743000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"google/gemini-4-argon","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":87.44,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_medscribe","value":0.8725,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":124,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_medscribe","value":0.8687999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":705,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_medscribe","value":0.8687,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":133,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"anthropic/claude-opus-4.6","source":"vals-more","metric":"vals_medscribe","value":0.8674,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"anthropic/claude-opus-4.6","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":54.32,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_medscribe","value":0.8653,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"x-ai/grok-4.6","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":70.94,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_medscribe","value":0.8645,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"openai/gpt-6.1-sol","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":170,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_medscribe","value":0.8575,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":82.36,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_medscribe","value":0.855,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":53.83,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_medscribe","value":0.8541,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":245,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-more","metric":"vals_medscribe","value":0.8532,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"anthropic/claude-opus-4.5","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":72.11,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_medscribe","value":0.8528,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":74.48,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_medscribe","value":0.8523000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":94.4,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_medscribe","value":0.8523000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":66.2,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_medscribe","value":0.8495,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":251,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-more","metric":"vals_medscribe","value":0.8452,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"anthropic/claude-sonnet-4.5","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":44.42,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_medscribe","value":0.845,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"google/gemini-3.8-flash","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":21.14,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_medscribe","value":0.8439,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":116.89,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"openai/gpt-5.2","source":"vals-more","metric":"vals_medscribe","value":0.8439,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"openai/gpt-5.2","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":126,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_medscribe","value":0.8411,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":230,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_medscribe","value":0.8393999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"google/gemini-3.7-flash","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":16.82,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_medscribe","value":0.8384999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"qwen/qwen3.8-27b","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":89.7,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_medscribe","value":0.8373,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":90.71,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_medscribe","value":0.8371,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"openai/gpt-6-luna","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":170,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"openai/gpt-5","source":"vals-more","metric":"vals_medscribe","value":0.8365,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"openai/gpt-5","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":185,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_medscribe","value":0.836,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"tencent/hy4-preview","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":350,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_medscribe","value":0.8353,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"z-ai/glm-5.2","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":138,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"google/gemini-2.5-flash","source":"vals-more","metric":"vals_medscribe","value":0.8298000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"google/gemini-2.5-flash","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":22.53,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_medscribe","value":0.8295,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":67.5,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_medscribe","value":0.8287,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":35.53,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_medscribe","value":0.8203,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"openai/gpt-6-sol","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":81.14,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_medscribe","value":0.809,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"inclusionai/ling-3.0-flash","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":12.12,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"minimax/minimax-m2.1","source":"vals-more","metric":"vals_medscribe","value":0.8078,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"minimax/minimax-m2.1","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":53.16,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"openai/gpt-5-mini","source":"vals-more","metric":"vals_medscribe","value":0.8058,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"openai/gpt-5-mini","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":276,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_medscribe","value":0.8043,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"mistralai/mistral-large-4-0","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":125,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_medscribe","value":0.8036,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":77.55,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_medscribe","value":0.8017,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":156,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_medscribe","value":0.7987000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"minimax/minimax-m2.7","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":27.25,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_medscribe","value":0.7966,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":33.55,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_medscribe","value":0.794,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"qwen/qwen3.7-max","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":108.05,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_medscribe","value":0.7815000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":494,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_medscribe","value":0.7755,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"openai/gpt-5.4","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":283,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_medscribe","value":0.7709,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":20.53,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_medscribe","value":0.7696,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":174,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"openai/o3","source":"vals-more","metric":"vals_medscribe","value":0.7665000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"openai/o3","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":46.39,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_medscribe","value":0.7656999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":57.08,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_medscribe","value":0.7644,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"moonshotai/kimi-k2.5","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":147,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_medscribe","value":0.7611,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":69.14,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_medscribe","value":0.7605,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":252,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"google/gemini-2.5-flash-lite","source":"vals-more","metric":"vals_medscribe","value":0.7582,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"google/gemini-2.5-flash-lite","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":4.49,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_medscribe","value":0.7514,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"deepseek/deepseek-v4-pro","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":346,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_medscribe","value":0.7440000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":100.46,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"anthropic/claude-opus-4.1","source":"vals-more","metric":"vals_medscribe","value":0.7390000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"anthropic/claude-opus-4.1","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":57.4,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"google/gemini-2.5-pro","source":"vals-more","metric":"vals_medscribe","value":0.7354999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"google/gemini-2.5-pro","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":35.91,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"openai/gpt-5-nano","source":"vals-more","metric":"vals_medscribe","value":0.7286,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"openai/gpt-5-nano","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":112.91,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_medscribe","value":0.7227,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"z-ai/glm-5.1","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":95.7,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_medscribe","value":0.7215,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":20.26,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_medscribe","value":0.7089,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"google/gemini-3.5-flash-lite","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":18.99,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"vals-more","metric":"vals_medscribe","value":0.7062,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":80.41,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_medscribe","value":0.6992,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":23.49,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"openai/o4-mini","source":"vals-more","metric":"vals_medscribe","value":0.6914,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"openai/o4-mini","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":81.96,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"z-ai/glm-4.7","source":"vals-more","metric":"vals_medscribe","value":0.6862999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"z-ai/glm-4.7","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":167,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_medscribe","value":0.6773,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":104.05,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_medscribe","value":0.639,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":16.79,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_medscribe","value":0.6341,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":18.6,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"cohere/command-a","source":"vals-more","metric":"vals_medscribe","value":0.5568,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"cohere/command-a","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":203,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_medscribe","value":0.5509000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"inception/mercury-2.5","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":9.99,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"meta-llama/llama-4-maverick","source":"vals-more","metric":"vals_medscribe","value":0.5422,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"meta-llama/llama-4-maverick","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":25.05,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"meta-llama/llama-4-scout","source":"vals-more","metric":"vals_medscribe","value":0.5059,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"meta-llama/llama-4-scout","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":11.32,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"vals-more","metric":"vals_medscribe","value":0.042699999999999995,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"nvidia/nemotron-3.5-lightning","source":"vals-more","metric":"vals_medscribe_latency_seconds","value":105.52,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/medscribe"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_multimodal_index","value":0.7415,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_multimodal_index_cost_per_test_usd","value":7.97,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"anthropic/claude-fable-5","source":"vals-more","metric":"vals_multimodal_index_duration_seconds","value":769,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_multimodal_index","value":0.7390000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_multimodal_index_cost_per_test_usd","value":6.14,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"anthropic/claude-opus-5","source":"vals-more","metric":"vals_multimodal_index_duration_seconds","value":854,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_multimodal_index","value":0.7342,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_multimodal_index_cost_per_test_usd","value":1.7,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"moonshotai/kimi-k3","source":"vals-more","metric":"vals_multimodal_index_duration_seconds","value":906,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_multimodal_index","value":0.7264,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_multimodal_index_cost_per_test_usd","value":5.36,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"openai/gpt-5.6-sol","source":"vals-more","metric":"vals_multimodal_index_duration_seconds","value":551,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_multimodal_index","value":0.7089,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_multimodal_index_cost_per_test_usd","value":5.46,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"anthropic/claude-opus-4.8","source":"vals-more","metric":"vals_multimodal_index_duration_seconds","value":980,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_multimodal_index","value":0.698,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_multimodal_index_cost_per_test_usd","value":0.51,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"meta/muse-spark-1.2","source":"vals-more","metric":"vals_multimodal_index_duration_seconds","value":446,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_multimodal_index","value":0.6906,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_multimodal_index_cost_per_test_usd","value":0.16,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"openai/gpt-5.6-luna","source":"vals-more","metric":"vals_multimodal_index_duration_seconds","value":407,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_multimodal_index","value":0.6883,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_multimodal_index_cost_per_test_usd","value":6.53,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"anthropic/claude-sonnet-5","source":"vals-more","metric":"vals_multimodal_index_duration_seconds","value":1012,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_multimodal_index","value":0.6807,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_multimodal_index_cost_per_test_usd","value":3.32,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"openai/gpt-5.5","source":"vals-more","metric":"vals_multimodal_index_duration_seconds","value":504,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_multimodal_index","value":0.6736,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_multimodal_index_cost_per_test_usd","value":4.44,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"anthropic/claude-opus-4.7","source":"vals-more","metric":"vals_multimodal_index_duration_seconds","value":564,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_multimodal_index","value":0.6674,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_multimodal_index_cost_per_test_usd","value":0.36,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"meta/muse-spark-1.1","source":"vals-more","metric":"vals_multimodal_index_duration_seconds","value":288,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_multimodal_index","value":0.6539,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_multimodal_index_cost_per_test_usd","value":1.93,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"qwen/qwen3.8-max-0902","source":"vals-more","metric":"vals_multimodal_index_duration_seconds","value":1996,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_multimodal_index","value":0.6507999999999999,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_multimodal_index_cost_per_test_usd","value":1.02,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"google/gemini-3.6-flash","source":"vals-more","metric":"vals_multimodal_index_duration_seconds","value":536,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_multimodal_index","value":0.6507,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_multimodal_index_cost_per_test_usd","value":0.8,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"openai/gpt-5.6-terra","source":"vals-more","metric":"vals_multimodal_index_duration_seconds","value":258,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_multimodal_index","value":0.6342,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_multimodal_index_cost_per_test_usd","value":0.91,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"x-ai/grok-4.5","source":"vals-more","metric":"vals_multimodal_index_duration_seconds","value":319,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_multimodal_index","value":0.6293,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_multimodal_index_cost_per_test_usd","value":1.01,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"google/gemini-3.5-flash","source":"vals-more","metric":"vals_multimodal_index_duration_seconds","value":266,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_multimodal_index","value":0.6057,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_multimodal_index_cost_per_test_usd","value":1.58,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"anthropic/claude-sonnet-4.6","source":"vals-more","metric":"vals_multimodal_index_duration_seconds","value":536,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_multimodal_index","value":0.5997,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_multimodal_index_cost_per_test_usd","value":1.08,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"minimax/minimax-m3","source":"vals-more","metric":"vals_multimodal_index_duration_seconds","value":1076,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_multimodal_index","value":0.5643,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_multimodal_index_cost_per_test_usd","value":0.52,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"moonshotai/kimi-k2.6","source":"vals-more","metric":"vals_multimodal_index_duration_seconds","value":904,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_multimodal_index","value":0.5607,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_multimodal_index_cost_per_test_usd","value":0.98,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"google/gemini-3.1-pro-preview","source":"vals-more","metric":"vals_multimodal_index_duration_seconds","value":323,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_multimodal_index","value":0.5422,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_multimodal_index_cost_per_test_usd","value":0.49,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"openai/gpt-5.4-mini","source":"vals-more","metric":"vals_multimodal_index_duration_seconds","value":788,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"qwen/qwen3.7-plus","source":"vals-more","metric":"vals_multimodal_index","value":0.5389,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"qwen/qwen3.7-plus","source":"vals-more","metric":"vals_multimodal_index_cost_per_test_usd","value":0.26,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"qwen/qwen3.7-plus","source":"vals-more","metric":"vals_multimodal_index_duration_seconds","value":629,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_multimodal_index","value":0.5277000000000001,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_multimodal_index_cost_per_test_usd","value":0.03,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"xiaomi/mimo-v2.5","source":"vals-more","metric":"vals_multimodal_index_duration_seconds","value":430,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_multimodal_index","value":0.5219,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_multimodal_index_cost_per_test_usd","value":0.29,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"google/gemini-3-flash-preview","source":"vals-more","metric":"vals_multimodal_index_duration_seconds","value":260,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_multimodal_index","value":0.5152,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_multimodal_index_cost_per_test_usd","value":1.12,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"qwen/qwen3.6-plus","source":"vals-more","metric":"vals_multimodal_index_duration_seconds","value":643,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_multimodal_index","value":0.5005,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_multimodal_index_cost_per_test_usd","value":0.14,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"thinkingmachines/inkling-small","source":"vals-more","metric":"vals_multimodal_index_duration_seconds","value":709,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_multimodal_index","value":0.494,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_multimodal_index_cost_per_test_usd","value":0.63,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"thinkingmachines/inkling","source":"vals-more","metric":"vals_multimodal_index_duration_seconds","value":929,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_multimodal_index","value":0.4764,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_multimodal_index_cost_per_test_usd","value":0.23,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"openai/gpt-5.4-nano","source":"vals-more","metric":"vals_multimodal_index_duration_seconds","value":671,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_multimodal_index","value":0.4329,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_multimodal_index_cost_per_test_usd","value":0.5,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"x-ai/grok-4.3","source":"vals-more","metric":"vals_multimodal_index_duration_seconds","value":339,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_multimodal_index","value":0.4288,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_multimodal_index_cost_per_test_usd","value":0.41,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"anthropic/claude-haiku-4.5","source":"vals-more","metric":"vals_multimodal_index_duration_seconds","value":283,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_multimodal_index","value":0.41350000000000003,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_multimodal_index_cost_per_test_usd","value":0.12,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"vals-more","metric":"vals_multimodal_index_duration_seconds","value":152,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_multimodal_index","value":0.3906,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_multimodal_index_cost_per_test_usd","value":0.4,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"x-ai/grok-4.20","source":"vals-more","metric":"vals_multimodal_index_duration_seconds","value":171,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_multimodal_index","value":0.3477,"unit":"ratio","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_multimodal_index_cost_per_test_usd","value":3.45,"unit":"usd","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"mistralai/mistral-medium-3-5","source":"vals-more","metric":"vals_multimodal_index_duration_seconds","value":735,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.vals.ai/benchmarks/vals_multimodal_index"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_elo","value":1532.3375436695164,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_elo_votes","value":4904,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_elo_interval","value":8.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_elo","value":1515.7614452392686,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_elo_votes","value":8300,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_elo_interval","value":7.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_elo","value":1511.5534589044762,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_elo_votes","value":14590,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_elo_interval","value":6.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_elo","value":1507.6361874165489,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_elo_votes","value":32495,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_elo_interval","value":4.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_elo","value":1501.6943977895103,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_elo_votes","value":81394,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_elo_interval","value":3.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_elo","value":1500.9554786587114,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_elo_votes","value":3247,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_elo_interval","value":10.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_elo","value":1498.8823435102179,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_elo_votes","value":37454,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_elo_interval","value":4.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_elo","value":1491.2265859286508,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_elo_votes","value":42004,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_elo_interval","value":4.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_elo","value":1490.6785014821505,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_elo_votes","value":4075,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_elo_interval","value":9.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_elo","value":1489.9962469201294,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_elo_votes","value":17561,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_elo_interval","value":5.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_elo","value":1489.754884516141,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_elo_votes","value":65116,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_elo_interval","value":3.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_elo","value":1487.3039513740575,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_elo_votes","value":27232,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_elo_interval","value":4.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_elo","value":1483.6337562562753,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_elo_votes","value":8248,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_elo_interval","value":7.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_elo","value":1482.8772252478664,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_elo_votes","value":27766,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_elo_interval","value":4.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_elo","value":1482.0166701667843,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_elo_votes","value":48486,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_elo_interval","value":3.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_elo","value":1480.1516865475448,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_elo_votes","value":127649,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_elo_interval","value":2.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_elo","value":1479.3122139856446,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_elo_votes","value":36122,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_elo_interval","value":4.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_elo","value":1478.0707420682486,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_elo_votes","value":42810,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_elo_interval","value":4.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_elo","value":1474.6645918511683,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_elo_votes","value":32795,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_elo_interval","value":4.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_elo","value":1471.3397664394297,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_elo_votes","value":69401,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_elo_interval","value":3.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_elo","value":1470.5296626495826,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_elo_votes","value":32925,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_elo_interval","value":4.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_elo","value":1470.3823826457517,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_elo_votes","value":6831,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_elo_interval","value":7.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_elo","value":1468.9734137454454,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_elo_votes","value":64776,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_elo_interval","value":3.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_elo","value":1464.885970353601,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_elo_votes","value":75721,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_elo_interval","value":3.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_elo","value":1462.4039016755132,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_elo_votes","value":62889,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_elo_interval","value":3.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_elo","value":1461.0756396737042,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_elo_votes","value":64100,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_elo_interval","value":3.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_elo","value":1457.8672969763822,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_elo_votes","value":70931,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_elo_interval","value":3.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_elo","value":1457.7258120664546,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_elo_votes","value":125366,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_elo_interval","value":2.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_elo","value":1457.0630136388463,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_elo_votes","value":40442,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_elo_interval","value":4.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_elo","value":1455.42205541913,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_elo_votes","value":40013,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_elo_interval","value":4.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_elo","value":1455.2141256062962,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_elo_votes","value":10917,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_elo_interval","value":6.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_elo","value":1454.5821410752708,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_elo_votes","value":42075,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_elo_interval","value":4.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_elo","value":1451.1584212632322,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_elo_votes","value":57594,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_elo_interval","value":3.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_elo","value":1450.8764850286768,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_elo_votes","value":72899,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_elo_interval","value":3.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_elo","value":1447.9704091358738,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_elo_votes","value":39896,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_elo_interval","value":4.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_elo","value":1447.3914205209428,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_elo_votes","value":43271,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_elo_interval","value":4.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_elo","value":1445.9283654823557,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_elo_votes","value":29272,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_elo_interval","value":4.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_elo","value":1442.8635409140436,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_elo_votes","value":6147,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_elo_interval","value":7.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_elo","value":1442.7372529317308,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_elo_votes","value":41651,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_elo_interval","value":3.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_elo","value":1442.12148050211,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_elo_votes","value":49595,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_elo_interval","value":4.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_elo","value":1441.3906418931479,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_elo_votes","value":7116,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_elo_interval","value":7.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_elo","value":1441.3843755522262,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_elo_votes","value":40648,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_elo_interval","value":4.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_elo","value":1440.5473201399373,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_elo_votes","value":23294,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_elo_interval","value":5.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_elo","value":1439.9166325391427,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_elo_votes","value":35824,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_elo_interval","value":3.89,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_elo","value":1438.4246824831582,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_elo_votes","value":82688,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_elo_interval","value":2.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_elo","value":1438.0013487945234,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_elo_votes","value":12208,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_elo_interval","value":6.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_elo","value":1437.7189287176805,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_elo_votes","value":93567,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_elo_interval","value":3.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_elo","value":1437.602304534889,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_elo_votes","value":10482,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_elo_interval","value":6.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_elo","value":1436.363981628608,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_elo_votes","value":48165,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_elo_interval","value":4.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_elo","value":1435.4043769505327,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_elo_votes","value":12253,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_elo_interval","value":6.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_elo","value":1434.5162611299957,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_elo_votes","value":35851,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_elo_interval","value":4.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_elo","value":1434.1159973589392,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_elo_votes","value":6094,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_elo_interval","value":7.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_elo","value":1433.3266154552236,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_elo_votes","value":63973,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_elo_interval","value":3.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_elo","value":1431.8376632131556,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_elo_votes","value":51987,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_elo_interval","value":4.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_elo","value":1430.6557406021043,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_elo_votes","value":41109,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_elo_interval","value":4.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_elo","value":1429.9946133933556,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_elo_votes","value":7451,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_elo_interval","value":7.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_elo","value":1429.9410054562568,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_elo_votes","value":23796,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_elo_interval","value":4.89,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_elo","value":1427.7652036468833,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_elo_votes","value":28965,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_elo_interval","value":4.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_elo","value":1427.728299546782,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_elo_votes","value":47362,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_elo_interval","value":4.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_elo","value":1427.703156098861,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_elo_votes","value":18167,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_elo_interval","value":5.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_elo","value":1424.4567637120713,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_elo_votes","value":48112,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_elo_interval","value":3.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_elo","value":1422.1755624052087,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_elo_votes","value":12004,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_elo_interval","value":6.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_elo","value":1420.966198360955,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_elo_votes","value":11778,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_elo_interval","value":6.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_elo","value":1420.0930479615047,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_elo_votes","value":11320,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_elo_interval","value":6.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_elo","value":1419.1275223666578,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_elo_votes","value":98134,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_elo_interval","value":2.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_elo","value":1418.6469693382608,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_elo_votes","value":77238,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_elo_interval","value":2.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_elo","value":1417.3957431608792,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_elo_votes","value":29732,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_elo_interval","value":4.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_elo","value":1417.1045316510745,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_elo_votes","value":3608,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_elo_interval","value":9.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_elo","value":1417.0229015581779,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_elo_votes","value":22760,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_elo_interval","value":4.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_elo","value":1416.8914386105444,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_elo_votes","value":125521,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_elo_interval","value":2.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_elo","value":1416.241155836213,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_elo_votes","value":49655,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_elo_interval","value":3.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_elo","value":1415.8118820268242,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_elo_votes","value":64211,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_elo_interval","value":3.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_elo","value":1415.044224579377,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_elo_votes","value":8823,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_elo_interval","value":6.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_elo","value":1412.6234189082622,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_elo_votes","value":32304,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_elo_interval","value":4.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_elo","value":1411.451300466027,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_elo_votes","value":63449,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_elo_interval","value":3.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_elo","value":1409.8213257617233,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_elo_votes","value":58908,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_elo_interval","value":3.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_elo","value":1408.8984198274281,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_elo_votes","value":28671,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_elo_interval","value":4.27,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_elo","value":1406.1806547025644,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_elo_votes","value":31722,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_elo_interval","value":4.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_elo","value":1404.8321223235982,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_elo_votes","value":84977,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_elo_interval","value":3.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_elo","value":1402.606049719976,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_elo_votes","value":60332,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_elo_interval","value":3.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_elo","value":1400.5236699479146,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_elo_votes","value":11591,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_elo_interval","value":6.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_elo","value":1397.0135676146804,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_elo_votes","value":61802,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_elo_interval","value":3.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_elo","value":1396.9237209726516,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_elo_votes","value":71347,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_elo_interval","value":3.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_elo","value":1396.6445118945935,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_elo_votes","value":149199,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_elo_interval","value":2.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_elo","value":1394.7323358127903,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_elo_votes","value":30457,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_elo_interval","value":4.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_elo","value":1386.7207226836342,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_elo_votes","value":21281,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_elo_interval","value":5.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_elo","value":1383.8322170927747,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_elo_votes","value":23322,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_elo_interval","value":4.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_elo","value":1383.6910402570022,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_elo_votes","value":30660,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_elo_interval","value":4.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_elo","value":1382.8918564209341,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_elo_votes","value":50312,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_elo_interval","value":3.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_elo","value":1377.5882655324158,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_elo_votes","value":7878,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_elo_interval","value":7.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_elo","value":1376.36652049651,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_elo_votes","value":2837,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_elo_interval","value":11.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_elo","value":1374.5908048889319,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_elo_votes","value":44973,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_elo_interval","value":3.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_elo","value":1373.2833088749294,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_elo_votes","value":26804,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_elo_interval","value":4.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_elo","value":1372.0134529059194,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_elo_votes","value":62396,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_elo_interval","value":3.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_elo","value":1368.0855703291281,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_elo_votes","value":13474,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_elo_interval","value":5.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_elo","value":1365.7881624179697,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_elo_votes","value":27807,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_elo_interval","value":4.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_elo","value":1365.5110682283662,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_elo_votes","value":30206,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_elo_interval","value":4.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_elo","value":1361.8256109457454,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_elo_votes","value":12413,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_elo_interval","value":6.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_elo","value":1359.1239335465827,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_elo_votes","value":42815,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_elo_interval","value":3.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_elo","value":1357.8020787106684,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_elo_votes","value":46666,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_elo_interval","value":3.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_elo","value":1356.5630184436598,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_elo_votes","value":25195,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_elo_interval","value":4.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_elo","value":1354.8601029761023,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_elo_votes","value":3197,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_elo_interval","value":10.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_elo","value":1353.2945502996856,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_elo_votes","value":44855,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_elo_interval","value":3.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_elo","value":1350.5622867972056,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_elo_votes","value":12021,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_elo_interval","value":5.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_elo","value":1342.6252470433112,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_elo_votes","value":34303,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_elo_interval","value":4.27,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_elo","value":1340.5047131542751,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_elo_votes","value":38709,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_elo_interval","value":4.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_elo","value":1340.1070986110035,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_elo_votes","value":30337,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_elo_interval","value":4.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_elo","value":1340.0739376589238,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_elo_votes","value":3926,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_elo_interval","value":9.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_elo","value":1339.9202475131674,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_elo_votes","value":6856,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_elo_interval","value":7.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_elo","value":1336.554249045414,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_elo_votes","value":18589,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_elo_interval","value":5.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_elo","value":1334.200514191159,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_elo_votes","value":3829,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_elo_interval","value":9.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_elo","value":1332.6508301539218,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_elo_votes","value":4821,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_elo_interval","value":8.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_elo","value":1330.9389119376765,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_elo_votes","value":55766,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_elo_interval","value":3.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_elo","value":1319.937017746315,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_elo_votes","value":8132,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_elo_interval","value":6.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_elo","value":1319.5785614364268,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_elo_votes","value":3254,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_elo_interval","value":11.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_elo","value":1319.4198519851786,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_elo_votes","value":56741,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_elo_interval","value":3.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_elo","value":1317.0052518000293,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_elo_votes","value":26157,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_elo_interval","value":4.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_elo","value":1300.3973861265524,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_elo_votes","value":112881,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_elo_interval","value":3.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_elo","value":1290.7831372470387,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_elo_votes","value":4171,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_elo_interval","value":9.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_elo","value":1287.4250454920798,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_elo_votes","value":10419,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_elo_interval","value":6.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_elo","value":1287.1891774182086,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_elo_votes","value":39450,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_elo_interval","value":4.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_elo","value":1286.342818557726,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_elo_votes","value":68705,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_elo_interval","value":3.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_elo","value":1284.7769429877421,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_elo_votes","value":6103,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_elo_interval","value":7.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_elo","value":1282.5032001179243,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_elo_votes","value":45499,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_elo_interval","value":4.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_elo","value":1279.1579685442514,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_elo_votes","value":29826,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_elo_interval","value":4.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_elo","value":1277.1347186281205,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_elo_votes","value":32727,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_elo_interval","value":4.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_elo","value":1274.2054326702603,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_elo_votes","value":54497,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_elo_interval","value":3.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_elo","value":1268.9804569233395,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_elo_votes","value":39406,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_elo_interval","value":4.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_elo","value":1266.1069767363372,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_elo_votes","value":45459,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_elo_interval","value":3.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_elo","value":1260.8692263664682,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_elo_votes","value":55240,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_elo_interval","value":3.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_elo","value":1233.5332116485577,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_elo_votes","value":14681,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_elo_interval","value":5.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_elo","value":1231.3419387831543,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_elo_votes","value":75754,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_elo_interval","value":3.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_elo","value":1230.005014483507,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_elo_votes","value":5432,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_elo_interval","value":8.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_elo","value":1228.860539744157,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_elo_votes","value":9866,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_elo_interval","value":6.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_elo","value":1216.655292750256,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_elo_votes","value":24126,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_elo_interval","value":4.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_elo","value":1187.3209642971283,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_elo_votes","value":10140,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_elo_interval","value":6.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_elo","value":1186.5393457001621,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_elo_votes","value":49605,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_elo_interval","value":4.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_elo","value":1109.4952152415176,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_elo_votes","value":7936,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_elo_interval","value":7.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_elo","value":1054.5956379993384,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_elo_votes","value":8045,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_elo_interval","value":7.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_coding_elo","value":1546.7188161621557,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_coding_elo_votes","value":1231,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_coding_elo_interval","value":17.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_coding_elo","value":1545.1394344198627,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_coding_elo_votes","value":1894,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_coding_elo_interval","value":13.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_coding_elo","value":1534.5009470417847,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_coding_elo_votes","value":23838,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_coding_elo_interval","value":5.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_coding_elo","value":1533.2230944859175,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_coding_elo_votes","value":8148,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_coding_elo_interval","value":7.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_coding_elo","value":1532.3932110701055,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_coding_elo_votes","value":1105,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_coding_elo_interval","value":17.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_coding_elo","value":1530.8862079510498,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_coding_elo_votes","value":2900,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_coding_elo_interval","value":11.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_coding_elo","value":1520.104588947746,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_coding_elo_votes","value":776,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_coding_elo_interval","value":20.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_coding_elo","value":1518.5054629434212,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_coding_elo_votes","value":18573,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_coding_elo_interval","value":5.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_coding_elo","value":1518.1284060166283,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_coding_elo_votes","value":10844,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_coding_elo_interval","value":6.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_coding_elo","value":1513.0389356039466,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_coding_elo_votes","value":1627,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_coding_elo_interval","value":14.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_coding_elo","value":1510.3185120031317,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_coding_elo_votes","value":4556,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_coding_elo_interval","value":9.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_coding_elo","value":1507.5798781832048,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_coding_elo_votes","value":8457,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_coding_elo_interval","value":7.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_coding_elo","value":1507.348540639942,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_coding_elo_votes","value":9810,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_coding_elo_interval","value":7.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_coding_elo","value":1506.6150403428828,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_coding_elo_votes","value":8306,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_coding_elo_interval","value":7.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_coding_elo","value":1503.5503102970426,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_coding_elo_votes","value":19724,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_coding_elo_interval","value":5.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_coding_elo","value":1502.7506421484643,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_coding_elo_votes","value":2170,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_coding_elo_interval","value":12.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_coding_elo","value":1502.043888212294,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_coding_elo_votes","value":2625,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_coding_elo_interval","value":11.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_coding_elo","value":1502.042829023629,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_coding_elo_votes","value":20404,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_coding_elo_interval","value":5.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_coding_elo","value":1501.9343868248368,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_coding_elo_votes","value":7677,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_coding_elo_interval","value":7.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_coding_elo","value":1498.5751438349575,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_coding_elo_votes","value":17986,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_coding_elo_interval","value":5.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_coding_elo","value":1498.3356802484602,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_coding_elo_votes","value":7459,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_coding_elo_interval","value":7.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_coding_elo","value":1497.3880950807757,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_coding_elo_votes","value":11856,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_coding_elo_interval","value":6.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_coding_elo","value":1496.472639423631,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_coding_elo_votes","value":10825,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_coding_elo_interval","value":6.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_coding_elo","value":1496.442165273631,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_coding_elo_votes","value":17600,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_coding_elo_interval","value":5.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_coding_elo","value":1494.2965884865876,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_coding_elo_votes","value":19167,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_coding_elo_interval","value":5.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_coding_elo","value":1493.223107074158,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_coding_elo_votes","value":13847,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_coding_elo_interval","value":6.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_coding_elo","value":1491.2378325570648,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_coding_elo_votes","value":10368,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_coding_elo_interval","value":6.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_coding_elo","value":1490.691133935009,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_coding_elo_votes","value":17427,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_coding_elo_interval","value":5.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_coding_elo","value":1488.763957989253,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_coding_elo_votes","value":11091,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_coding_elo_interval","value":6.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_coding_elo","value":1485.3534387557538,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_coding_elo_votes","value":17133,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_coding_elo_interval","value":5.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_coding_elo","value":1484.9027382958368,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_coding_elo_votes","value":1719,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_coding_elo_interval","value":14.08,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_coding_elo","value":1484.8737057132626,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_coding_elo_votes","value":11499,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_coding_elo_interval","value":6.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_coding_elo","value":1484.64214508908,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_coding_elo_votes","value":19782,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_coding_elo_interval","value":4.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_coding_elo","value":1483.5296365630359,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_coding_elo_votes","value":35033,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_coding_elo_interval","value":4.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_coding_elo","value":1483.4554850471848,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_coding_elo_votes","value":13270,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_coding_elo_interval","value":6.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_coding_elo","value":1482.713860008716,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_coding_elo_votes","value":6417,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_coding_elo_interval","value":7.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_coding_elo","value":1480.8866497823562,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_coding_elo_votes","value":1685,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_coding_elo_interval","value":14.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_coding_elo","value":1473.9838219537546,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_coding_elo_votes","value":11116,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_coding_elo_interval","value":6.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_coding_elo","value":1472.7233283585601,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_coding_elo_votes","value":15695,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_coding_elo_interval","value":5.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_coding_elo","value":1472.644852600176,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_coding_elo_votes","value":12183,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_coding_elo_interval","value":6.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_coding_elo","value":1471.3421157005346,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_coding_elo_votes","value":18242,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_coding_elo_interval","value":5.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_coding_elo","value":1469.322993147524,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_coding_elo_votes","value":17136,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_coding_elo_interval","value":5.89,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_coding_elo","value":1469.0256810666967,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_coding_elo_votes","value":13656,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_coding_elo_interval","value":6.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_coding_elo","value":1466.6707273320014,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_coding_elo_votes","value":14688,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_coding_elo_interval","value":6.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_coding_elo","value":1466.5295448220356,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_coding_elo_votes","value":2944,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_coding_elo_interval","value":11.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_coding_elo","value":1466.3576016434718,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_coding_elo_votes","value":11127,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_coding_elo_interval","value":6.6,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_coding_elo","value":1465.4267660221365,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_coding_elo_votes","value":11078,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_coding_elo_interval","value":6.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_coding_elo","value":1465.3225064886444,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_coding_elo_votes","value":7222,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_coding_elo_interval","value":7.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_coding_elo","value":1465.3081061488726,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_coding_elo_votes","value":3329,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_coding_elo_interval","value":10.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_coding_elo","value":1464.449600029706,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_coding_elo_votes","value":26519,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_coding_elo_interval","value":4.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_coding_elo","value":1461.0837361215908,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_coding_elo_votes","value":7637,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_coding_elo_interval","value":7.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_coding_elo","value":1460.794098254764,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_coding_elo_votes","value":3293,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_coding_elo_interval","value":10.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_coding_elo","value":1459.2197551861882,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_coding_elo_votes","value":1418,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_coding_elo_interval","value":14.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_coding_elo","value":1456.6094647710804,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_coding_elo_votes","value":15288,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_coding_elo_interval","value":6.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_coding_elo","value":1454.3539323387852,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_coding_elo_votes","value":2486,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_coding_elo_interval","value":11.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_coding_elo","value":1454.3375080818557,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_coding_elo_votes","value":24097,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_coding_elo_interval","value":5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_coding_elo","value":1453.5044369397274,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_coding_elo_votes","value":38427,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_coding_elo_interval","value":3.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_coding_elo","value":1453.2803789922089,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_coding_elo_votes","value":8411,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_coding_elo_interval","value":6.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_coding_elo","value":1452.688303005096,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_coding_elo_votes","value":9924,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_coding_elo_interval","value":6.89,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_coding_elo","value":1451.5781734638017,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_coding_elo_votes","value":26964,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_coding_elo_interval","value":4.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_coding_elo","value":1451.5119760931595,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_coding_elo_votes","value":8848,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_coding_elo_interval","value":7.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_coding_elo","value":1448.8957988797242,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_coding_elo_votes","value":10923,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_coding_elo_interval","value":6.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_coding_elo","value":1448.6425071972349,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_coding_elo_votes","value":7602,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_coding_elo_interval","value":7.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_coding_elo","value":1446.4298217436385,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_coding_elo_votes","value":1445,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_coding_elo_interval","value":14.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_coding_elo","value":1444.5146039836627,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_coding_elo_votes","value":21747,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_coding_elo_interval","value":4.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_coding_elo","value":1441.5905144451349,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_coding_elo_votes","value":12245,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_coding_elo_interval","value":6.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_coding_elo","value":1440.4825518930254,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_coding_elo_votes","value":4817,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_coding_elo_interval","value":8.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_coding_elo","value":1438.703452457685,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_coding_elo_votes","value":5517,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_coding_elo_interval","value":8.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_coding_elo","value":1438.5015330754727,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_coding_elo_votes","value":2313,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_coding_elo_interval","value":12.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_coding_elo","value":1438.3590513012064,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_coding_elo_votes","value":17236,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_coding_elo_interval","value":5.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_coding_elo","value":1436.0379089074393,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_coding_elo_votes","value":6400,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_coding_elo_interval","value":7.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_coding_elo","value":1435.86662027418,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_coding_elo_votes","value":8187,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_coding_elo_interval","value":7.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_coding_elo","value":1435.6720229192642,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_coding_elo_votes","value":15192,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_coding_elo_interval","value":5.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_coding_elo","value":1435.2153169788135,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_coding_elo_votes","value":2552,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_coding_elo_interval","value":11.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_coding_elo","value":1434.0737825925833,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_coding_elo_votes","value":4742,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_coding_elo_interval","value":8.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_coding_elo","value":1431.657780992084,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_coding_elo_votes","value":2522,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_coding_elo_interval","value":12.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_coding_elo","value":1426.8955917363687,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_coding_elo_votes","value":2690,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_coding_elo_interval","value":11.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_coding_elo","value":1426.3625046866268,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_coding_elo_votes","value":7939,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_coding_elo_interval","value":7.08,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_coding_elo","value":1424.2788322905112,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_coding_elo_votes","value":1591,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_coding_elo_interval","value":14.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_coding_elo","value":1423.5209286667118,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_coding_elo_votes","value":26379,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_coding_elo_interval","value":4.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_coding_elo","value":1415.9214400943433,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_coding_elo_votes","value":4614,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_coding_elo_interval","value":8.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_coding_elo","value":1414.7549419516424,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_coding_elo_votes","value":19950,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_coding_elo_interval","value":5.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_coding_elo","value":1412.108611848728,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_coding_elo_votes","value":4809,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_coding_elo_interval","value":8.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_coding_elo","value":1411.833504205846,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_coding_elo_votes","value":17719,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_coding_elo_interval","value":5.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_coding_elo","value":1409.827645731157,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_coding_elo_votes","value":8395,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_coding_elo_interval","value":7.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_coding_elo","value":1407.4537405480582,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_coding_elo_votes","value":11583,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_coding_elo_interval","value":6.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_coding_elo","value":1406.7985018774314,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_coding_elo_votes","value":771,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_coding_elo_interval","value":20.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_coding_elo","value":1405.7808199130664,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_coding_elo_votes","value":5520,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_coding_elo_interval","value":8.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_coding_elo","value":1404.3840829364824,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_coding_elo_votes","value":17665,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_coding_elo_interval","value":5.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_coding_elo","value":1403.2614549614257,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_coding_elo_votes","value":1884,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_coding_elo_interval","value":13.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_coding_elo","value":1399.9974166860397,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_coding_elo_votes","value":17855,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_coding_elo_interval","value":5.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_coding_elo","value":1397.0934066316001,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_coding_elo_votes","value":6101,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_coding_elo_interval","value":7.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_coding_elo","value":1391.5200812154796,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_coding_elo_votes","value":2667,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_coding_elo_interval","value":11.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_coding_elo","value":1390.7215748451822,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_coding_elo_votes","value":9248,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_coding_elo_interval","value":6.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_coding_elo","value":1390.1748159018705,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_coding_elo_votes","value":802,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_coding_elo_interval","value":20.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_coding_elo","value":1389.4668021609236,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_coding_elo_votes","value":545,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_coding_elo_interval","value":24.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_coding_elo","value":1385.3158225765706,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_coding_elo_votes","value":2580,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_coding_elo_interval","value":11.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_coding_elo","value":1382.3765794250755,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_coding_elo_votes","value":2795,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_coding_elo_interval","value":10.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_coding_elo","value":1380.3810049746676,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_coding_elo_votes","value":11358,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_coding_elo_interval","value":6.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_coding_elo","value":1379.4721651770406,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_coding_elo_votes","value":6410,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_coding_elo_interval","value":7.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_coding_elo","value":1378.599949338821,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_coding_elo_votes","value":831,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_coding_elo_interval","value":21.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_coding_elo","value":1377.983628452944,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_coding_elo_votes","value":2596,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_coding_elo_interval","value":11.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_coding_elo","value":1370.1678910372611,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_coding_elo_votes","value":1550,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_coding_elo_interval","value":14.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_coding_elo","value":1368.1402762804053,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_coding_elo_votes","value":8655,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_coding_elo_interval","value":6.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_coding_elo","value":1367.7464572172023,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_coding_elo_votes","value":8334,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_coding_elo_interval","value":6.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_coding_elo","value":1367.0658719903765,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_coding_elo_votes","value":6822,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_coding_elo_interval","value":7.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_coding_elo","value":1366.7206058201568,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_coding_elo_votes","value":3973,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_coding_elo_interval","value":9.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_coding_elo","value":1362.8124198228868,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_coding_elo_votes","value":9400,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_coding_elo_interval","value":6.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_coding_elo","value":1358.5600442393834,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_coding_elo_votes","value":6400,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_coding_elo_interval","value":7.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_coding_elo","value":1357.549436144077,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_coding_elo_votes","value":8550,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_coding_elo_interval","value":7.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_coding_elo","value":1357.4491454447536,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_coding_elo_votes","value":513,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_coding_elo_interval","value":24.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_coding_elo","value":1351.1354128956102,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_coding_elo_votes","value":1664,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_coding_elo_interval","value":14.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_coding_elo","value":1347.5381253647765,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_coding_elo_votes","value":965,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_coding_elo_interval","value":18.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_coding_elo","value":1336.6255092853362,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_coding_elo_votes","value":4503,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_coding_elo_interval","value":8.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_coding_elo","value":1330.0149779169376,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_coding_elo_votes","value":10234,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_coding_elo_interval","value":6.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_coding_elo","value":1321.9036580222973,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_coding_elo_votes","value":8021,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_coding_elo_interval","value":6.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_coding_elo","value":1308.7907074105249,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_coding_elo_votes","value":6115,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_coding_elo_interval","value":7.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_coding_elo","value":1306.5240120530455,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_coding_elo_votes","value":2112,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_coding_elo_interval","value":13.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_coding_elo","value":1305.4788465919596,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_coding_elo_votes","value":807,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_coding_elo_interval","value":19.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_coding_elo","value":1301.401667252504,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_coding_elo_votes","value":6940,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_coding_elo_interval","value":7.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_coding_elo","value":1296.9568211126118,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_coding_elo_votes","value":19526,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_coding_elo_interval","value":6.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_coding_elo","value":1292.2577065691933,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_coding_elo_votes","value":6688,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_coding_elo_interval","value":7.6,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_coding_elo","value":1289.4690896239529,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_coding_elo_votes","value":10928,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_coding_elo_interval","value":6.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_coding_elo","value":1285.8637920704077,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_coding_elo_votes","value":5227,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_coding_elo_interval","value":8.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_coding_elo","value":1283.3331183214257,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_coding_elo_votes","value":7318,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_coding_elo_interval","value":7.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_coding_elo","value":1280.9759596607144,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_coding_elo_votes","value":543,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_coding_elo_interval","value":22.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_coding_elo","value":1276.4478067788,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_coding_elo_votes","value":7589,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_coding_elo_interval","value":7.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_coding_elo","value":1275.4515095820323,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_coding_elo_votes","value":873,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_coding_elo_interval","value":18.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_coding_elo","value":1267.9259960293102,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_coding_elo_votes","value":8735,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_coding_elo_interval","value":6.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_coding_elo","value":1259.4921645572767,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_coding_elo_votes","value":9389,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_coding_elo_interval","value":7.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_coding_elo","value":1245.5522891339403,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_coding_elo_votes","value":2083,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_coding_elo_interval","value":12.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_coding_elo","value":1231.133605990181,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_coding_elo_votes","value":3305,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_coding_elo_interval","value":9.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_coding_elo","value":1230.0501981769526,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_coding_elo_votes","value":605,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_coding_elo_interval","value":23.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_coding_elo","value":1210.7384005013796,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_coding_elo_votes","value":12088,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_coding_elo_interval","value":6.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_coding_elo","value":1194.6160307735952,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_coding_elo_votes","value":8582,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_coding_elo_interval","value":7.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_coding_elo","value":1186.8961011098709,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_coding_elo_votes","value":1675,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_coding_elo_interval","value":13.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_coding_elo","value":1169.248352252048,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_coding_elo_votes","value":1783,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_coding_elo_interval","value":13.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_coding_elo","value":1097.5273785138365,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_coding_elo_votes","value":1351,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_coding_elo_interval","value":15.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_coding_elo","value":1070.325889064139,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_coding_elo_votes","value":1346,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_coding_elo_interval","value":15.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_hard_prompts_elo","value":1546.0047529403569,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_hard_prompts_elo_votes","value":3129,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_hard_prompts_elo_interval","value":10.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_hard_prompts_elo","value":1534.9214273102377,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_hard_prompts_elo_votes","value":5157,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_hard_prompts_elo_interval","value":8.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_hard_prompts_elo","value":1526.4628554189014,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_hard_prompts_elo_votes","value":21001,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_hard_prompts_elo","value":1526.4063544653575,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_hard_prompts_elo_votes","value":8511,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_hard_prompts_elo_interval","value":7.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_hard_prompts_elo","value":1525.4988598754253,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_hard_prompts_elo_votes","value":51834,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_hard_prompts_elo_interval","value":4.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_hard_prompts_elo","value":1510.2087555247604,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_hard_prompts_elo_votes","value":2624,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_hard_prompts_elo_interval","value":11.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_hard_prompts_elo","value":1509.7057562373866,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_hard_prompts_elo_votes","value":2018,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_hard_prompts_elo_interval","value":13.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_hard_prompts_elo","value":1508.7307351605546,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_hard_prompts_elo_votes","value":24169,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_hard_prompts_elo","value":1507.3118693173549,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_hard_prompts_elo_votes","value":27374,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_hard_prompts_elo_interval","value":4.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_hard_prompts_elo","value":1505.7644599897114,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_hard_prompts_elo_votes","value":43663,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_hard_prompts_elo_interval","value":4.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_hard_prompts_elo","value":1501.7834590008415,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_hard_prompts_elo_votes","value":11392,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_hard_prompts_elo_interval","value":6.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_hard_prompts_elo","value":1495.3159203687983,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_hard_prompts_elo_votes","value":18366,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_hard_prompts_elo","value":1495.080521172832,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_hard_prompts_elo_votes","value":17784,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_hard_prompts_elo","value":1494.4415394501593,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_hard_prompts_elo_votes","value":21003,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_hard_prompts_elo","value":1492.5406825483506,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_hard_prompts_elo_votes","value":4222,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_hard_prompts_elo_interval","value":9.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_hard_prompts_elo","value":1490.3645035035265,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_hard_prompts_elo_votes","value":20935,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_hard_prompts_elo","value":1490.0497414594522,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_hard_prompts_elo_votes","value":5255,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_hard_prompts_elo_interval","value":8.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_hard_prompts_elo","value":1488.7566549281355,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_hard_prompts_elo_votes","value":45575,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_hard_prompts_elo_interval","value":4.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_hard_prompts_elo","value":1488.155702757445,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_hard_prompts_elo_votes","value":32403,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_hard_prompts_elo_interval","value":4.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_hard_prompts_elo","value":1486.497949641391,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_hard_prompts_elo_votes","value":49426,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_hard_prompts_elo_interval","value":4.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_hard_prompts_elo","value":1485.8350270807055,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_hard_prompts_elo_votes","value":28272,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_hard_prompts_elo_interval","value":4.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_hard_prompts_elo","value":1485.391051646818,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_hard_prompts_elo_votes","value":24166,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_hard_prompts_elo","value":1484.8709877298068,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_hard_prompts_elo_votes","value":42140,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_hard_prompts_elo_interval","value":4.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_hard_prompts_elo","value":1484.7467753841058,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_hard_prompts_elo_votes","value":82971,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_hard_prompts_elo_interval","value":3.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_hard_prompts_elo","value":1484.667043177535,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_hard_prompts_elo_votes","value":46229,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_hard_prompts_elo_interval","value":4.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_hard_prompts_elo","value":1483.328182621354,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_hard_prompts_elo_votes","value":26312,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_hard_prompts_elo","value":1481.8225974255447,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_hard_prompts_elo_votes","value":42534,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_hard_prompts_elo_interval","value":4.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_hard_prompts_elo","value":1478.7685352965675,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_hard_prompts_elo_votes","value":6781,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_hard_prompts_elo_interval","value":7.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_hard_prompts_elo","value":1476.143339480637,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_hard_prompts_elo_votes","value":43250,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_hard_prompts_elo_interval","value":3.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_hard_prompts_elo","value":1472.4258954212555,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_hard_prompts_elo_votes","value":41196,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_hard_prompts_elo_interval","value":4.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_hard_prompts_elo","value":1470.4243417395448,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_hard_prompts_elo_votes","value":26068,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_hard_prompts_elo","value":1468.376552399598,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_hard_prompts_elo_votes","value":28222,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_hard_prompts_elo_interval","value":4.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_hard_prompts_elo","value":1462.048042765525,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_hard_prompts_elo_votes","value":26662,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_hard_prompts_elo","value":1461.7472893426198,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_hard_prompts_elo_votes","value":48326,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_hard_prompts_elo_interval","value":3.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_hard_prompts_elo","value":1461.3010455899407,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_hard_prompts_elo_votes","value":38511,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_hard_prompts_elo_interval","value":4.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_hard_prompts_elo","value":1460.9349104907603,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_hard_prompts_elo_votes","value":32631,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_hard_prompts_elo_interval","value":4.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_hard_prompts_elo","value":1460.8847496053527,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_hard_prompts_elo_votes","value":4458,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_hard_prompts_elo_interval","value":9.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_hard_prompts_elo","value":1459.5706756963737,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_hard_prompts_elo_votes","value":28316,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_hard_prompts_elo_interval","value":4.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_hard_prompts_elo","value":1459.1345109954068,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_hard_prompts_elo_votes","value":15193,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_hard_prompts_elo","value":1456.943429586748,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_hard_prompts_elo_votes","value":22414,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_hard_prompts_elo_interval","value":4.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_hard_prompts_elo","value":1454.7549217354012,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_hard_prompts_elo_votes","value":65927,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_hard_prompts_elo_interval","value":3.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_hard_prompts_elo","value":1451.5828737652812,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_hard_prompts_elo_votes","value":18210,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_hard_prompts_elo","value":1451.3951849070836,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_hard_prompts_elo_votes","value":26664,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_hard_prompts_elo","value":1451.2995007497623,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_hard_prompts_elo_votes","value":27008,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_hard_prompts_elo","value":1450.0350559302922,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_hard_prompts_elo_votes","value":31849,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_hard_prompts_elo_interval","value":4.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_hard_prompts_elo","value":1448.3909221250988,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_hard_prompts_elo_votes","value":32584,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_hard_prompts_elo_interval","value":4.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_hard_prompts_elo","value":1447.9023927481305,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_hard_prompts_elo_votes","value":42422,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_hard_prompts_elo_interval","value":4.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_hard_prompts_elo","value":1447.7767163158906,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_hard_prompts_elo_votes","value":61654,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_hard_prompts_elo_interval","value":3.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_hard_prompts_elo","value":1447.7504258298559,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_hard_prompts_elo_votes","value":3573,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_hard_prompts_elo_interval","value":9.6,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_hard_prompts_elo","value":1447.2355764882977,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_hard_prompts_elo_votes","value":8110,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_hard_prompts_elo_interval","value":7.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_hard_prompts_elo","value":1446.9380590991063,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_hard_prompts_elo_votes","value":18782,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_hard_prompts_elo","value":1443.783027487591,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_hard_prompts_elo_votes","value":6953,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_hard_prompts_elo_interval","value":7.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_hard_prompts_elo","value":1443.559256230479,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_hard_prompts_elo_votes","value":4626,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_hard_prompts_elo_interval","value":9.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_hard_prompts_elo","value":1443.3815385473797,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_hard_prompts_elo_votes","value":34768,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_hard_prompts_elo_interval","value":4.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_hard_prompts_elo","value":1442.8557882175596,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_hard_prompts_elo_votes","value":6796,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_hard_prompts_elo_interval","value":7.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_hard_prompts_elo","value":1442.1446942372263,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_hard_prompts_elo_votes","value":39442,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_hard_prompts_elo_interval","value":3.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_hard_prompts_elo","value":1440.299046898966,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_hard_prompts_elo_votes","value":23813,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_hard_prompts_elo","value":1440.1532411428464,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_hard_prompts_elo_votes","value":19455,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_hard_prompts_elo_interval","value":4.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_hard_prompts_elo","value":1438.4810048741458,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_hard_prompts_elo_votes","value":3473,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_hard_prompts_elo_interval","value":9.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_hard_prompts_elo","value":1436.6744605435158,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_hard_prompts_elo_votes","value":7648,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_hard_prompts_elo_interval","value":7.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_hard_prompts_elo","value":1433.5521879589744,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_hard_prompts_elo_votes","value":27086,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_hard_prompts_elo_interval","value":4.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_hard_prompts_elo","value":1433.3373778607133,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_hard_prompts_elo_votes","value":53546,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_hard_prompts_elo_interval","value":3.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_hard_prompts_elo","value":1429.1242279519704,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_hard_prompts_elo_votes","value":11110,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_hard_prompts_elo_interval","value":6.36,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_hard_prompts_elo","value":1428.854652701771,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_hard_prompts_elo_votes","value":6584,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_hard_prompts_elo_interval","value":7.89,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_hard_prompts_elo","value":1428.2838563714215,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_hard_prompts_elo_votes","value":5706,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_hard_prompts_elo_interval","value":8.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_hard_prompts_elo","value":1427.9797044459563,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_hard_prompts_elo_votes","value":29889,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_hard_prompts_elo_interval","value":4.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_hard_prompts_elo","value":1427.477887646026,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_hard_prompts_elo_votes","value":11995,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_hard_prompts_elo","value":1424.2537035548194,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_hard_prompts_elo_votes","value":41651,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_hard_prompts_elo_interval","value":4.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_hard_prompts_elo","value":1422.722731324971,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_hard_prompts_elo_votes","value":55278,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_hard_prompts_elo_interval","value":3.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_hard_prompts_elo","value":1422.5149805825133,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_hard_prompts_elo_votes","value":21129,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_hard_prompts_elo","value":1422.1138666630475,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_hard_prompts_elo_votes","value":65147,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_hard_prompts_elo_interval","value":3.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_hard_prompts_elo","value":1421.2382185213742,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_hard_prompts_elo_votes","value":18806,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_hard_prompts_elo","value":1420.1526693967637,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_hard_prompts_elo_votes","value":92034,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_hard_prompts_elo_interval","value":3.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_hard_prompts_elo","value":1415.709865750121,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_hard_prompts_elo_votes","value":3807,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_hard_prompts_elo_interval","value":9.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_hard_prompts_elo","value":1415.4822428955054,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_hard_prompts_elo_votes","value":7054,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_hard_prompts_elo_interval","value":7.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_hard_prompts_elo","value":1415.4434571129923,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_hard_prompts_elo_votes","value":15057,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_hard_prompts_elo","value":1415.351970730578,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_hard_prompts_elo_votes","value":6880,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_hard_prompts_elo_interval","value":7.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_hard_prompts_elo","value":1414.3357484683158,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_hard_prompts_elo_votes","value":18084,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_hard_prompts_elo","value":1410.6154054657961,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_hard_prompts_elo_votes","value":37552,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_hard_prompts_elo_interval","value":4.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_hard_prompts_elo","value":1407.4290736326857,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_hard_prompts_elo_votes","value":41615,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_hard_prompts_elo_interval","value":4.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_hard_prompts_elo","value":1405.9323077571498,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_hard_prompts_elo_votes","value":1902,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_hard_prompts_elo_interval","value":13.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_hard_prompts_elo","value":1403.4404168861956,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_hard_prompts_elo_votes","value":40131,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_hard_prompts_elo_interval","value":4.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_hard_prompts_elo","value":1402.0470141170138,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_hard_prompts_elo_votes","value":25530,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_hard_prompts_elo_interval","value":4.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_hard_prompts_elo","value":1399.8584925617872,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_hard_prompts_elo_votes","value":19334,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_hard_prompts_elo","value":1398.999811891415,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_hard_prompts_elo_votes","value":13795,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_hard_prompts_elo_interval","value":6.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_hard_prompts_elo","value":1397.7857990825196,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_hard_prompts_elo_votes","value":10978,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_hard_prompts_elo_interval","value":6.27,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_hard_prompts_elo","value":1396.5235403647928,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_hard_prompts_elo_votes","value":47680,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_hard_prompts_elo_interval","value":4.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_hard_prompts_elo","value":1386.2801073825267,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_hard_prompts_elo_votes","value":4399,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_hard_prompts_elo_interval","value":8.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_hard_prompts_elo","value":1384.0939482301342,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_hard_prompts_elo_votes","value":22029,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_hard_prompts_elo_interval","value":4.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_hard_prompts_elo","value":1380.4715511920026,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_hard_prompts_elo_votes","value":41331,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_hard_prompts_elo_interval","value":4.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_hard_prompts_elo","value":1379.9571391448533,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_hard_prompts_elo_votes","value":12861,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_hard_prompts_elo","value":1378.6901727768793,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_hard_prompts_elo_votes","value":14892,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_hard_prompts_elo","value":1372.0210397768733,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_hard_prompts_elo_votes","value":26877,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_hard_prompts_elo_interval","value":4.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_hard_prompts_elo","value":1371.863956998085,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_hard_prompts_elo_votes","value":11533,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_hard_prompts_elo_interval","value":6.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_hard_prompts_elo","value":1371.3544127547684,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_hard_prompts_elo_votes","value":6453,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_hard_prompts_elo_interval","value":7.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_hard_prompts_elo","value":1371.3229853105956,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_hard_prompts_elo_votes","value":6662,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_hard_prompts_elo_interval","value":7.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_hard_prompts_elo","value":1367.5709433835173,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_hard_prompts_elo_votes","value":1536,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_hard_prompts_elo_interval","value":14.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_hard_prompts_elo","value":1365.3994079127956,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_hard_prompts_elo_votes","value":4386,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_hard_prompts_elo_interval","value":9.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_hard_prompts_elo","value":1364.773415945698,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_hard_prompts_elo_votes","value":18588,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_hard_prompts_elo","value":1364.0282013083065,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_hard_prompts_elo_votes","value":6635,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_hard_prompts_elo_interval","value":7.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_hard_prompts_elo","value":1363.4984435625122,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_hard_prompts_elo_votes","value":14685,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_hard_prompts_elo","value":1361.6822910749736,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_hard_prompts_elo_votes","value":1850,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_hard_prompts_elo_interval","value":13.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_hard_prompts_elo","value":1356.7177853429155,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_hard_prompts_elo_votes","value":3744,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_hard_prompts_elo_interval","value":9.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_hard_prompts_elo","value":1355.9304505779312,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_hard_prompts_elo_votes","value":6745,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_hard_prompts_elo_interval","value":7.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_hard_prompts_elo","value":1350.486547977577,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_hard_prompts_elo_votes","value":19388,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_hard_prompts_elo","value":1348.8071204510493,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_hard_prompts_elo_votes","value":16071,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_hard_prompts_elo","value":1341.8609410118622,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_hard_prompts_elo_votes","value":20056,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_hard_prompts_elo","value":1340.2579112124859,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_hard_prompts_elo_votes","value":17699,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_hard_prompts_elo","value":1339.2764733450708,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_hard_prompts_elo_votes","value":15597,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_hard_prompts_elo","value":1334.4896582247932,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_hard_prompts_elo_votes","value":2346,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_hard_prompts_elo_interval","value":12.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_hard_prompts_elo","value":1334.3876878560602,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_hard_prompts_elo_votes","value":1207,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_hard_prompts_elo_interval","value":15.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_hard_prompts_elo","value":1332.6061128783606,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_hard_prompts_elo_votes","value":19989,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_hard_prompts_elo_interval","value":4.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_hard_prompts_elo","value":1328.4298474687214,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_hard_prompts_elo_votes","value":3779,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_hard_prompts_elo_interval","value":9.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_hard_prompts_elo","value":1327.3399168478406,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_hard_prompts_elo_votes","value":2077,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_hard_prompts_elo_interval","value":13.89,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_hard_prompts_elo","value":1326.3573317288578,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_hard_prompts_elo_votes","value":23760,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_hard_prompts_elo_interval","value":4.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_hard_prompts_elo","value":1313.984485602397,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_hard_prompts_elo_votes","value":10643,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_hard_prompts_elo_interval","value":6.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_hard_prompts_elo","value":1309.2613675358618,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_hard_prompts_elo_votes","value":977,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_hard_prompts_elo_interval","value":17.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_hard_prompts_elo","value":1285.5619196233454,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_hard_prompts_elo_votes","value":1669,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_hard_prompts_elo_interval","value":13.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_hard_prompts_elo","value":1280.661673016559,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_hard_prompts_elo_votes","value":32416,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_hard_prompts_elo","value":1280.5884357445261,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_hard_prompts_elo_votes","value":15870,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_hard_prompts_elo","value":1277.6445812938061,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_hard_prompts_elo_votes","value":14625,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_hard_prompts_elo","value":1273.7523443503926,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_hard_prompts_elo_votes","value":4718,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_hard_prompts_elo_interval","value":8.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_hard_prompts_elo","value":1270.470575549192,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_hard_prompts_elo_votes","value":10545,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_hard_prompts_elo_interval","value":6.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_hard_prompts_elo","value":1266.8435532402373,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_hard_prompts_elo_votes","value":18259,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_hard_prompts_elo","value":1266.031263623529,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_hard_prompts_elo_votes","value":12901,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_hard_prompts_elo_interval","value":6.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_hard_prompts_elo","value":1263.8402186164917,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_hard_prompts_elo_votes","value":12655,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_hard_prompts_elo_interval","value":6.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_hard_prompts_elo","value":1257.0166934701863,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_hard_prompts_elo_votes","value":16961,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_hard_prompts_elo_interval","value":4.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_hard_prompts_elo","value":1256.3382075345398,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_hard_prompts_elo_votes","value":12682,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_hard_prompts_elo_interval","value":6.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_hard_prompts_elo","value":1252.5157256555215,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_hard_prompts_elo_votes","value":1092,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_hard_prompts_elo_interval","value":17.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_hard_prompts_elo","value":1251.1306204737418,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_hard_prompts_elo_votes","value":1386,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_hard_prompts_elo_interval","value":14.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_hard_prompts_elo","value":1241.071257610783,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_hard_prompts_elo_votes","value":14981,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_hard_prompts_elo","value":1232.9656438765203,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_hard_prompts_elo_votes","value":3569,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_hard_prompts_elo_interval","value":9.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_hard_prompts_elo","value":1219.4547385198637,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_hard_prompts_elo_votes","value":5747,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_hard_prompts_elo_interval","value":7.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_hard_prompts_elo","value":1198.2166612943577,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_hard_prompts_elo_votes","value":20494,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_hard_prompts_elo_interval","value":5.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_hard_prompts_elo","value":1185.415246494644,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_hard_prompts_elo_votes","value":2822,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_hard_prompts_elo_interval","value":10.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_hard_prompts_elo","value":1174.5463456253876,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_hard_prompts_elo_votes","value":13535,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_hard_prompts_elo_interval","value":6.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_hard_prompts_elo","value":1164.0683256747056,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_hard_prompts_elo_votes","value":2976,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_hard_prompts_elo_interval","value":10.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_hard_prompts_elo","value":1094.5007127574797,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_hard_prompts_elo_votes","value":2216,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_hard_prompts_elo_interval","value":12.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_hard_prompts_elo","value":1044.1259067421743,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_hard_prompts_elo_votes","value":2247,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_hard_prompts_elo_interval","value":12.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_math_elo","value":1536.2779658740383,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_math_elo_votes","value":273,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_math_elo_interval","value":34.27,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_math_elo","value":1531.8979783118534,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_math_elo_votes","value":3152,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_math_elo_interval","value":11.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_math_elo","value":1528.4415633231174,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_math_elo_votes","value":695,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_math_elo_interval","value":21.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_math_elo","value":1527.4311625249443,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_math_elo_votes","value":1883,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_math_elo_interval","value":14.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_math_elo","value":1518.6177393782177,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_math_elo_votes","value":4186,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_math_elo_interval","value":9.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_math_elo","value":1518.5843240349527,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_math_elo_votes","value":2069,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_math_elo_interval","value":13.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_math_elo","value":1509.9732451213486,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_math_elo_votes","value":1390,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_math_elo_interval","value":16.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_math_elo","value":1508.029395291393,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_math_elo_votes","value":416,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_math_elo_interval","value":28.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_math_elo","value":1505.5111489760438,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_math_elo_votes","value":1764,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_math_elo_interval","value":14.08,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_math_elo","value":1504.5131400860937,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_math_elo_votes","value":1647,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_math_elo_interval","value":14.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_math_elo","value":1503.2073822211746,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_math_elo_votes","value":2385,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_math_elo_interval","value":12.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_math_elo","value":1501.7988870143108,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_math_elo_votes","value":1401,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_math_elo_interval","value":15.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_math_elo","value":1499.3668780737303,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_math_elo_votes","value":215,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_math_elo_interval","value":39.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_math_elo","value":1498.639068956401,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_math_elo_votes","value":345,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_math_elo_interval","value":31.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_math_elo","value":1498.5623566833042,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_math_elo_votes","value":3286,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_math_elo_interval","value":10.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_math_elo","value":1496.4422850329465,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_math_elo_votes","value":854,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_math_elo_interval","value":19.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_math_elo","value":1494.4113706646094,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_math_elo_votes","value":1458,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_math_elo_interval","value":15.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_math_elo","value":1487.382051709883,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_math_elo_votes","value":3379,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_math_elo_interval","value":10.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_math_elo","value":1487.0568598537989,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_math_elo_votes","value":3511,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_math_elo_interval","value":10.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_math_elo","value":1486.184732920649,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_math_elo_votes","value":2969,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_math_elo_interval","value":11.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_math_elo","value":1485.1651713604692,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_math_elo_votes","value":6622,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_math_elo_interval","value":7.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_math_elo","value":1483.6204250893325,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_math_elo_votes","value":1960,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_math_elo_interval","value":13.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_math_elo","value":1481.3534666120772,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_math_elo_votes","value":3608,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_math_elo_interval","value":10.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_math_elo","value":1477.315739171635,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_math_elo_votes","value":1845,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_math_elo_interval","value":13.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_math_elo","value":1475.9049044198978,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_math_elo_votes","value":411,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_math_elo_interval","value":28.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_math_elo","value":1474.739881305065,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_math_elo_votes","value":2074,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_math_elo_interval","value":13.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_math_elo","value":1474.1659183369925,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_math_elo_votes","value":576,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_math_elo_interval","value":23.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_math_elo","value":1473.203928773406,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_math_elo_votes","value":1902,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_math_elo_interval","value":13.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_math_elo","value":1473.0027145724466,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_math_elo_votes","value":3088,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_math_elo_interval","value":11.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_math_elo","value":1470.8546927153325,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_math_elo_votes","value":662,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_math_elo_interval","value":22.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_math_elo","value":1469.6875037275781,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_math_elo_votes","value":390,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_math_elo_interval","value":27.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_math_elo","value":1469.193220499857,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_math_elo_votes","value":377,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_math_elo_interval","value":29.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_math_elo","value":1467.2685124343907,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_math_elo_votes","value":2246,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_math_elo_interval","value":12.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_math_elo","value":1467.2396296417623,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_math_elo_votes","value":1910,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_math_elo_interval","value":13.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_math_elo","value":1464.5142385771014,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_math_elo_votes","value":1946,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_math_elo_interval","value":13.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_math_elo","value":1464.2312043145057,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_math_elo_votes","value":430,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_math_elo_interval","value":26.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_math_elo","value":1462.695895644275,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_math_elo_votes","value":3792,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_math_elo_interval","value":10,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_math_elo","value":1459.035612905002,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_math_elo_votes","value":1766,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_math_elo_interval","value":14.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_math_elo","value":1458.9698423433192,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_math_elo_votes","value":1927,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_math_elo_interval","value":13.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_math_elo","value":1458.1589123404765,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_math_elo_votes","value":4547,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_math_elo_interval","value":8.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_math_elo","value":1457.4727604229824,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_math_elo_votes","value":1455,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_math_elo_interval","value":15.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_math_elo","value":1456.7867881935122,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_math_elo_votes","value":1171,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_math_elo_interval","value":17.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_math_elo","value":1453.5935261854806,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_math_elo_votes","value":5146,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_math_elo_interval","value":8.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_math_elo","value":1451.6253041497307,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_math_elo_votes","value":350,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_math_elo_interval","value":30.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_math_elo","value":1449.814977618612,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_math_elo_votes","value":2690,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_math_elo_interval","value":11.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_math_elo","value":1449.7721916232636,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_math_elo_votes","value":7817,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_math_elo_interval","value":6.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_math_elo","value":1446.1762159215887,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_math_elo_votes","value":2579,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_math_elo_interval","value":11.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_math_elo","value":1442.7990079224478,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_math_elo_votes","value":3063,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_math_elo_interval","value":11.08,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_math_elo","value":1441.299983093416,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_math_elo_votes","value":486,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_math_elo_interval","value":25.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_math_elo","value":1440.0511083129645,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_math_elo_votes","value":1204,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_math_elo_interval","value":16.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_math_elo","value":1440.0074364923116,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_math_elo_votes","value":1694,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_math_elo_interval","value":14.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_math_elo","value":1439.8050577023341,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_math_elo_votes","value":3127,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_math_elo_interval","value":10.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_math_elo","value":1436.0374541320798,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_math_elo_votes","value":2460,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_math_elo_interval","value":12.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_math_elo","value":1435.1820820799776,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_math_elo_votes","value":3141,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_math_elo_interval","value":10.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_math_elo","value":1433.2174932126868,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_math_elo_votes","value":1624,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_math_elo_interval","value":14.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_math_elo","value":1431.9639812683558,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_math_elo_votes","value":2153,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_math_elo_interval","value":12.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_math_elo","value":1431.5316979291633,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_math_elo_votes","value":6077,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_math_elo_interval","value":7.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_math_elo","value":1431.311968877404,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_math_elo_votes","value":1845,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_math_elo_interval","value":13.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_math_elo","value":1431.1708837177175,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_math_elo_votes","value":565,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_math_elo_interval","value":24.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_math_elo","value":1429.3196706688213,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_math_elo_votes","value":3192,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_math_elo_interval","value":10.89,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_math_elo","value":1429.0962152232478,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_math_elo_votes","value":1746,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_math_elo_interval","value":14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_math_elo","value":1427.8654723406216,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_math_elo_votes","value":3622,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_math_elo_interval","value":10.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_math_elo","value":1427.2437785609418,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_math_elo_votes","value":1402,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_math_elo_interval","value":15.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_math_elo","value":1426.458962151974,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_math_elo_votes","value":2697,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_math_elo_interval","value":11.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_math_elo","value":1426.407475008904,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_math_elo_votes","value":3701,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_math_elo_interval","value":9.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_math_elo","value":1425.2849705603007,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_math_elo_votes","value":700,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_math_elo_interval","value":22.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_math_elo","value":1423.9479885176206,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_math_elo_votes","value":739,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_math_elo_interval","value":20.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_math_elo","value":1422.0387036307552,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_math_elo_votes","value":5125,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_math_elo_interval","value":8.36,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_math_elo","value":1421.785448342498,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_math_elo_votes","value":4806,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_math_elo_interval","value":8.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_math_elo","value":1420.2687253759805,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_math_elo_votes","value":4268,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_math_elo_interval","value":9.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_math_elo","value":1419.8909822143041,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_math_elo_votes","value":1056,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_math_elo_interval","value":18.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_math_elo","value":1418.627559694085,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_math_elo_votes","value":3367,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_math_elo_interval","value":10.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_math_elo","value":1418.1811038341257,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_math_elo_votes","value":793,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_math_elo_interval","value":19.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_math_elo","value":1416.3521993125778,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_math_elo_votes","value":1421,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_math_elo_interval","value":15.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_math_elo","value":1412.3358146211099,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_math_elo_votes","value":590,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_math_elo_interval","value":23.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_math_elo","value":1412.2133839175362,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_math_elo_votes","value":479,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_math_elo_interval","value":24.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_math_elo","value":1410.6201329811051,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_math_elo_votes","value":8004,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_math_elo_interval","value":6.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_math_elo","value":1408.1726313338554,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_math_elo_votes","value":3425,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_math_elo_interval","value":10.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_math_elo","value":1407.5115129215706,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_math_elo_votes","value":3386,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_math_elo_interval","value":10.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_math_elo","value":1406.841548295437,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_math_elo_votes","value":1779,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_math_elo_interval","value":13.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_math_elo","value":1405.9422622235415,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_math_elo_votes","value":3264,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_math_elo_interval","value":10.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_math_elo","value":1404.12768815052,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_math_elo_votes","value":1850,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_math_elo_interval","value":13.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_math_elo","value":1401.8071790731556,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_math_elo_votes","value":216,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_math_elo_interval","value":38.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_math_elo","value":1400.0130782399065,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_math_elo_votes","value":861,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_math_elo_interval","value":19.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_math_elo","value":1398.581598436002,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_math_elo_votes","value":316,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_math_elo_interval","value":29.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_math_elo","value":1398.3532684180987,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_math_elo_votes","value":823,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_math_elo_interval","value":19.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_math_elo","value":1396.6993673333232,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_math_elo_votes","value":8311,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_math_elo_interval","value":7.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_math_elo","value":1395.7063885380226,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_math_elo_votes","value":1909,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_math_elo_interval","value":13.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_math_elo","value":1395.5388156937643,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_math_elo_votes","value":1529,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_math_elo_interval","value":14.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_math_elo","value":1394.572495025005,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_math_elo_votes","value":1395,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_math_elo_interval","value":15.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_math_elo","value":1389.3102648478903,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_math_elo_votes","value":2916,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_math_elo_interval","value":10.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_math_elo","value":1388.5343795572103,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_math_elo_votes","value":1780,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_math_elo_interval","value":13.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_math_elo","value":1388.3374219954535,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_math_elo_votes","value":2986,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_math_elo_interval","value":10.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_math_elo","value":1387.1916313764532,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_math_elo_votes","value":3416,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_math_elo_interval","value":10.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_math_elo","value":1380.206158642567,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_math_elo_votes","value":547,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_math_elo_interval","value":24.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_math_elo","value":1377.6660381298434,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_math_elo_votes","value":2556,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_math_elo_interval","value":11.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_math_elo","value":1377.4004261980776,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_math_elo_votes","value":1457,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_math_elo_interval","value":15.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_math_elo","value":1373.9750992094207,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_math_elo_votes","value":4699,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_math_elo_interval","value":8.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_math_elo","value":1372.5509124848145,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_math_elo_votes","value":3166,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_math_elo_interval","value":10.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_math_elo","value":1369.2727094449206,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_math_elo_votes","value":3229,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_math_elo_interval","value":10.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_math_elo","value":1365.5929334462683,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_math_elo_votes","value":1718,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_math_elo_interval","value":14.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_math_elo","value":1365.2012461479196,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_math_elo_votes","value":1610,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_math_elo_interval","value":14.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_math_elo","value":1360.9341188182675,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_math_elo_votes","value":1770,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_math_elo_interval","value":13.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_math_elo","value":1358.6943710962105,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_math_elo_votes","value":861,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_math_elo_interval","value":19.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_math_elo","value":1355.3088617281994,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_math_elo_votes","value":756,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_math_elo_interval","value":20.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_math_elo","value":1354.5933694319347,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_math_elo_votes","value":1706,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_math_elo_interval","value":13.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_math_elo","value":1353.6548261590742,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_math_elo_votes","value":269,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_math_elo_interval","value":34.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_math_elo","value":1350.8512033470392,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_math_elo_votes","value":320,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_math_elo_interval","value":32.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_math_elo","value":1342.451914655906,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_math_elo_votes","value":2673,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_math_elo_interval","value":11.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_math_elo","value":1317.4396741514552,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_math_elo_votes","value":494,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_math_elo_interval","value":26.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_math_elo","value":1316.8123239528907,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_math_elo_votes","value":677,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_math_elo_interval","value":22.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_math_elo","value":1312.1487193015214,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_math_elo_votes","value":3587,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_math_elo_interval","value":9.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_math_elo","value":1307.4228290363028,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_math_elo_votes","value":389,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_math_elo_interval","value":26.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_math_elo","value":1300.2607430096205,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_math_elo_votes","value":3994,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_math_elo_interval","value":9.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_math_elo","value":1299.3317293416023,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_math_elo_votes","value":2825,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_math_elo_interval","value":10.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_math_elo","value":1286.849655636844,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_math_elo_votes","value":1942,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_math_elo_interval","value":13.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_math_elo","value":1285.2846722039562,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_math_elo_votes","value":6826,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_math_elo_interval","value":8.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_math_elo","value":1284.3076953020407,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_math_elo_votes","value":15103,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_math_elo_interval","value":6.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_math_elo","value":1282.527632960084,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_math_elo_votes","value":5415,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_math_elo_interval","value":8.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_math_elo","value":1274.3306352359127,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_math_elo_votes","value":582,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_math_elo_interval","value":22.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_math_elo","value":1267.3166558996995,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_math_elo_votes","value":9322,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_math_elo_interval","value":7.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_math_elo","value":1267.0323439687295,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_math_elo_votes","value":5778,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_math_elo_interval","value":7.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_math_elo","value":1261.4365671673995,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_math_elo_votes","value":6664,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_math_elo_interval","value":8.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_math_elo","value":1261.1820629504987,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_math_elo_votes","value":2105,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_math_elo_interval","value":13.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_math_elo","value":1251.5981707578817,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_math_elo_votes","value":7677,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_math_elo_interval","value":7.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_math_elo","value":1250.4704672408584,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_math_elo_votes","value":725,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_math_elo_interval","value":19.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_math_elo","value":1245.7562652276724,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_math_elo_votes","value":2764,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_math_elo_interval","value":10.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_math_elo","value":1240.1853294331931,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_math_elo_votes","value":1683,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_math_elo_interval","value":13.36,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_math_elo","value":1239.1658479476669,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_math_elo_votes","value":423,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_math_elo_interval","value":27.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_math_elo","value":1211.9322863075904,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_math_elo_votes","value":10170,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_math_elo_interval","value":6.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_math_elo","value":1187.768842908241,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_math_elo_votes","value":1467,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_math_elo_interval","value":13.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_math_elo","value":1179.1606665517131,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_math_elo_votes","value":7135,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_math_elo_interval","value":7.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_math_elo","value":1154.7889647764064,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_math_elo_votes","value":1601,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_math_elo_interval","value":13.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_math_elo","value":1125.845077449609,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_math_elo_votes","value":1136,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_math_elo_interval","value":15.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_math_elo","value":1085.6627708134192,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_math_elo_votes","value":1162,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_math_elo_interval","value":16.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_instruction_following_elo","value":1535.7834414387771,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_instruction_following_elo_votes","value":2851,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_instruction_following_elo_interval","value":11.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_instruction_following_elo","value":1535.627447733982,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_instruction_following_elo_votes","value":1750,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_instruction_following_elo_interval","value":14.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_instruction_following_elo","value":1521.9954193342442,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_instruction_following_elo_votes","value":26220,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_instruction_following_elo","value":1517.7535463181425,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_instruction_following_elo_votes","value":11298,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_instruction_following_elo_interval","value":6.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_instruction_following_elo","value":1517.208649784554,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_instruction_following_elo_votes","value":4370,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_instruction_following_elo_interval","value":9.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_instruction_following_elo","value":1502.3415238069006,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_instruction_following_elo_votes","value":14825,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_instruction_following_elo","value":1497.9832212237284,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_instruction_following_elo_votes","value":22744,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_instruction_following_elo","value":1490.9879403164764,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_instruction_following_elo_votes","value":13391,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_instruction_following_elo_interval","value":6.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_instruction_following_elo","value":1490.5232706542097,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_instruction_following_elo_votes","value":1395,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_instruction_following_elo_interval","value":15.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_instruction_following_elo","value":1488.4907233478316,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_instruction_following_elo_votes","value":2303,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_instruction_following_elo_interval","value":12.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_instruction_following_elo","value":1487.274315150727,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_instruction_following_elo_votes","value":1104,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_instruction_following_elo_interval","value":17.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_instruction_following_elo","value":1484.1956057125244,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_instruction_following_elo_votes","value":9766,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_instruction_following_elo_interval","value":7.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_instruction_following_elo","value":1483.4080867155112,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_instruction_following_elo_votes","value":10901,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_instruction_following_elo_interval","value":6.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_instruction_following_elo","value":1482.3125987306476,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_instruction_following_elo_votes","value":14119,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_instruction_following_elo_interval","value":6.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_instruction_following_elo","value":1479.4176112019368,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_instruction_following_elo_votes","value":9874,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_instruction_following_elo_interval","value":6.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_instruction_following_elo","value":1478.4667009460209,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_instruction_following_elo_votes","value":24032,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.27,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_instruction_following_elo","value":1477.6769870639891,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_instruction_following_elo_votes","value":6317,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_instruction_following_elo_interval","value":8.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_instruction_following_elo","value":1477.6518138605907,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_instruction_following_elo_votes","value":11345,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_instruction_following_elo_interval","value":6.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_instruction_following_elo","value":1476.343211988732,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_instruction_following_elo_votes","value":22679,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_instruction_following_elo","value":1476.0172524358118,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_instruction_following_elo_votes","value":25349,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_instruction_following_elo","value":1475.977753872592,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_instruction_following_elo_votes","value":23711,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_instruction_following_elo","value":1472.4659571929174,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_instruction_following_elo_votes","value":21834,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_instruction_following_elo_interval","value":4.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_instruction_following_elo","value":1469.1270885615977,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_instruction_following_elo_votes","value":21877,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_instruction_following_elo","value":1467.1416866602917,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_instruction_following_elo_votes","value":17406,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_instruction_following_elo","value":1466.65167178188,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_instruction_following_elo_votes","value":13124,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_instruction_following_elo_interval","value":6.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_instruction_following_elo","value":1465.7669667938012,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_instruction_following_elo_votes","value":43642,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_instruction_following_elo_interval","value":4.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_instruction_following_elo","value":1461.5337670790732,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_instruction_following_elo_votes","value":2908,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_instruction_following_elo_interval","value":11.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_instruction_following_elo","value":1458.9359788384218,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_instruction_following_elo_votes","value":24371,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_instruction_following_elo_interval","value":4.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_instruction_following_elo","value":1457.119352692203,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_instruction_following_elo_votes","value":15285,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_instruction_following_elo","value":1456.1312974508496,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_instruction_following_elo_votes","value":3623,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_instruction_following_elo_interval","value":10.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_instruction_following_elo","value":1455.5273808702195,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_instruction_following_elo_votes","value":15379,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_instruction_following_elo","value":1452.435686738133,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_instruction_following_elo_votes","value":22045,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_instruction_following_elo_interval","value":5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_instruction_following_elo","value":1452.3547355386731,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_instruction_following_elo_votes","value":17466,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_instruction_following_elo","value":1451.0085709405835,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_instruction_following_elo_votes","value":13200,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_instruction_following_elo_interval","value":6.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_instruction_following_elo","value":1445.581287198223,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_instruction_following_elo_votes","value":14539,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_instruction_following_elo_interval","value":6.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_instruction_following_elo","value":1445.130114865809,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_instruction_following_elo_votes","value":20027,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_instruction_following_elo","value":1442.5618312659494,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_instruction_following_elo_votes","value":11162,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_instruction_following_elo_interval","value":6.27,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_instruction_following_elo","value":1439.577418474657,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_instruction_following_elo_votes","value":15033,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_instruction_following_elo","value":1437.3111897689214,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_instruction_following_elo_votes","value":14621,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_instruction_following_elo_interval","value":6.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_instruction_following_elo","value":1436.8037088006772,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_instruction_following_elo_votes","value":8237,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_instruction_following_elo_interval","value":7.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_instruction_following_elo","value":1436.6261696983597,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_instruction_following_elo_votes","value":2508,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_instruction_following_elo_interval","value":12.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_instruction_following_elo","value":1436.4866036488447,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_instruction_following_elo_votes","value":35220,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_instruction_following_elo_interval","value":3.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_instruction_following_elo","value":1434.5414954491484,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_instruction_following_elo_votes","value":16069,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_instruction_following_elo_interval","value":6.08,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_instruction_following_elo","value":1433.6275004607942,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_instruction_following_elo_votes","value":20779,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_instruction_following_elo_interval","value":4.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_instruction_following_elo","value":1433.4776642469415,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_instruction_following_elo_votes","value":1803,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_instruction_following_elo_interval","value":13.6,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_instruction_following_elo","value":1433.1758040828095,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_instruction_following_elo_votes","value":22259,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_instruction_following_elo","value":1430.5793572639777,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_instruction_following_elo_votes","value":10340,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_instruction_following_elo_interval","value":6.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_instruction_following_elo","value":1427.708980328804,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_instruction_following_elo_votes","value":9599,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_instruction_following_elo_interval","value":6.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_instruction_following_elo","value":1425.8534163305885,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_instruction_following_elo_votes","value":4417,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_instruction_following_elo_interval","value":9.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_instruction_following_elo","value":1424.8941157374002,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_instruction_following_elo_votes","value":14605,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_instruction_following_elo_interval","value":6.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_instruction_following_elo","value":1424.412173337706,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_instruction_following_elo_votes","value":16574,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_instruction_following_elo","value":1423.6267943550743,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_instruction_following_elo_votes","value":3699,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_instruction_following_elo_interval","value":10.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_instruction_following_elo","value":1423.12614444761,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_instruction_following_elo_votes","value":31992,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_instruction_following_elo_interval","value":4.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_instruction_following_elo","value":1420.80975275035,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_instruction_following_elo_votes","value":17963,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_instruction_following_elo","value":1420.6417877269732,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_instruction_following_elo_votes","value":2579,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_instruction_following_elo_interval","value":11.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_instruction_following_elo","value":1420.1441382339003,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_instruction_following_elo_votes","value":1738,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_instruction_following_elo_interval","value":13.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_instruction_following_elo","value":1418.998782522438,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_instruction_following_elo_votes","value":12907,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_instruction_following_elo_interval","value":6.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_instruction_following_elo","value":1415.2053317822715,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_instruction_following_elo_votes","value":3831,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_instruction_following_elo_interval","value":9.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_instruction_following_elo","value":1414.471257982544,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_instruction_following_elo_votes","value":47790,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_instruction_following_elo_interval","value":3.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_instruction_following_elo","value":1412.6331105226272,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_instruction_following_elo_votes","value":13567,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_instruction_following_elo","value":1412.0511101920279,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_instruction_following_elo_votes","value":3306,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_instruction_following_elo_interval","value":10.27,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_instruction_following_elo","value":1410.0941649665401,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_instruction_following_elo_votes","value":10293,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_instruction_following_elo_interval","value":6.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_instruction_following_elo","value":1409.2303750939795,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_instruction_following_elo_votes","value":15300,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_instruction_following_elo","value":1407.8025619641635,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_instruction_following_elo_votes","value":27846,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_instruction_following_elo_interval","value":4.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_instruction_following_elo","value":1407.5725579698487,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_instruction_following_elo_votes","value":3853,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_instruction_following_elo_interval","value":10.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_instruction_following_elo","value":1406.370924478132,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_instruction_following_elo_votes","value":2946,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_instruction_following_elo_interval","value":11.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_instruction_following_elo","value":1405.0969185968634,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_instruction_following_elo_votes","value":21734,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_instruction_following_elo","value":1405.0252605780875,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_instruction_following_elo_votes","value":28460,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_instruction_following_elo_interval","value":4.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_instruction_following_elo","value":1404.9560794082304,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_instruction_following_elo_votes","value":34837,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_instruction_following_elo_interval","value":3.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_instruction_following_elo","value":1404.0139444245656,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_instruction_following_elo_votes","value":6162,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_instruction_following_elo_interval","value":7.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_instruction_following_elo","value":1400.7020416601663,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_instruction_following_elo_votes","value":3391,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_instruction_following_elo_interval","value":10.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_instruction_following_elo","value":1399.2853207506191,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_instruction_following_elo_votes","value":9582,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_instruction_following_elo_interval","value":6.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_instruction_following_elo","value":1398.7449065594478,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_instruction_following_elo_votes","value":11768,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_instruction_following_elo_interval","value":6.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_instruction_following_elo","value":1392.6895697759119,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_instruction_following_elo_votes","value":9229,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_instruction_following_elo_interval","value":6.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_instruction_following_elo","value":1388.3352458477652,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_instruction_following_elo_votes","value":6412,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_instruction_following_elo_interval","value":7.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_instruction_following_elo","value":1388.0074952252512,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_instruction_following_elo_votes","value":8373,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_instruction_following_elo_interval","value":7.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_instruction_following_elo","value":1386.001107468766,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_instruction_following_elo_votes","value":2094,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_instruction_following_elo_interval","value":12.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_instruction_following_elo","value":1384.717112600083,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_instruction_following_elo_votes","value":19325,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_instruction_following_elo","value":1381.592564409826,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_instruction_following_elo_votes","value":4015,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_instruction_following_elo_interval","value":9.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_instruction_following_elo","value":1380.3591622486797,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_instruction_following_elo_votes","value":1019,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_instruction_following_elo_interval","value":17.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_instruction_following_elo","value":1379.47021660367,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_instruction_following_elo_votes","value":9934,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_instruction_following_elo_interval","value":6.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_instruction_following_elo","value":1377.2667912371262,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_instruction_following_elo_votes","value":21500,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_instruction_following_elo","value":1374.9305754182296,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_instruction_following_elo_votes","value":7654,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_instruction_following_elo_interval","value":7.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_instruction_following_elo","value":1374.543725267194,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_instruction_following_elo_votes","value":20300,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_instruction_following_elo","value":1367.743680323249,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_instruction_following_elo_votes","value":15503,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_instruction_following_elo","value":1367.187315505179,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_instruction_following_elo_votes","value":10246,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_instruction_following_elo_interval","value":6.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_instruction_following_elo","value":1366.762588521508,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_instruction_following_elo_votes","value":13304,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_instruction_following_elo","value":1365.6984810051695,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_instruction_following_elo_votes","value":25136,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_instruction_following_elo","value":1362.9910024216952,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_instruction_following_elo_votes","value":5971,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_instruction_following_elo_interval","value":7.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_instruction_following_elo","value":1362.0677958759343,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_instruction_following_elo_votes","value":21487,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_instruction_following_elo","value":1356.7781229241514,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_instruction_following_elo_votes","value":7012,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_instruction_following_elo_interval","value":7.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_instruction_following_elo","value":1355.5008195381115,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_instruction_following_elo_votes","value":6199,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_instruction_following_elo_interval","value":7.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_instruction_following_elo","value":1353.6649404839304,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_instruction_following_elo_votes","value":8201,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_instruction_following_elo_interval","value":6.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_instruction_following_elo","value":1352.867968253126,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_instruction_following_elo_votes","value":13776,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_instruction_following_elo","value":1350.9518510187231,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_instruction_following_elo_votes","value":756,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_instruction_following_elo_interval","value":21.08,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_instruction_following_elo","value":1347.4608857319438,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_instruction_following_elo_votes","value":2158,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_instruction_following_elo_interval","value":12.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_instruction_following_elo","value":1344.4625778367363,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_instruction_following_elo_votes","value":12410,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_instruction_following_elo","value":1343.3371753176862,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_instruction_following_elo_votes","value":3533,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_instruction_following_elo_interval","value":9.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_instruction_following_elo","value":1337.255719204231,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_instruction_following_elo_votes","value":6681,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_instruction_following_elo_interval","value":7.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_instruction_following_elo","value":1334.86209740998,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_instruction_following_elo_votes","value":3421,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_instruction_following_elo_interval","value":10.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_instruction_following_elo","value":1332.516806929617,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_instruction_following_elo_votes","value":10002,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_instruction_following_elo_interval","value":6.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_instruction_following_elo","value":1328.7797760048347,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_instruction_following_elo_votes","value":2022,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_instruction_following_elo_interval","value":12.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_instruction_following_elo","value":1327.95957743685,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_instruction_following_elo_votes","value":888,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_instruction_following_elo_interval","value":19.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_instruction_following_elo","value":1326.427053666228,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_instruction_following_elo_votes","value":3309,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_instruction_following_elo_interval","value":10.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_instruction_following_elo","value":1325.791917212739,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_instruction_following_elo_votes","value":10355,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_instruction_following_elo_interval","value":6.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_instruction_following_elo","value":1320.521487936719,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_instruction_following_elo_votes","value":12503,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_instruction_following_elo","value":1320.4748429553028,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_instruction_following_elo_votes","value":11885,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_instruction_following_elo_interval","value":6.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_instruction_following_elo","value":1317.9585761745188,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_instruction_following_elo_votes","value":7865,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_instruction_following_elo_interval","value":7.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_instruction_following_elo","value":1314.986735599692,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_instruction_following_elo_votes","value":16949,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_instruction_following_elo","value":1311.8253930839755,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_instruction_following_elo_votes","value":8644,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_instruction_following_elo_interval","value":6.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_instruction_following_elo","value":1310.4718959905713,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_instruction_following_elo_votes","value":1294,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_instruction_following_elo_interval","value":15.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_instruction_following_elo","value":1308.645792167234,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_instruction_following_elo_votes","value":15575,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_instruction_following_elo","value":1306.0521881336394,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_instruction_following_elo_votes","value":2023,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_instruction_following_elo_interval","value":13.08,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_instruction_following_elo","value":1304.6724686350885,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_instruction_following_elo_votes","value":858,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_instruction_following_elo_interval","value":18.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_instruction_following_elo","value":1300.7436248466342,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_instruction_following_elo_votes","value":1134,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_instruction_following_elo_interval","value":18.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_instruction_following_elo","value":1299.0785150477932,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_instruction_following_elo_votes","value":1145,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_instruction_following_elo_interval","value":16.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_instruction_following_elo","value":1283.3673891167612,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_instruction_following_elo_votes","value":6134,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_instruction_following_elo_interval","value":7.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_instruction_following_elo","value":1277.5148733587243,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_instruction_following_elo_votes","value":43766,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_instruction_following_elo_interval","value":4.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_instruction_following_elo","value":1266.9546028277377,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_instruction_following_elo_votes","value":10500,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_instruction_following_elo_interval","value":6.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_instruction_following_elo","value":1266.5266681890273,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_instruction_following_elo_votes","value":18305,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_instruction_following_elo","value":1266.3616078815967,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_instruction_following_elo_votes","value":2015,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_instruction_following_elo_interval","value":12.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_instruction_following_elo","value":1263.0701162677638,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_instruction_following_elo_votes","value":8047,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_instruction_following_elo_interval","value":7.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_instruction_following_elo","value":1258.2349220379556,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_instruction_following_elo_votes","value":26707,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_instruction_following_elo_interval","value":4.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_instruction_following_elo","value":1253.917902500726,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_instruction_following_elo_votes","value":16363,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_instruction_following_elo","value":1247.646526856261,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_instruction_following_elo_votes","value":18321,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_instruction_following_elo","value":1247.6230478177335,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_instruction_following_elo_votes","value":7477,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_instruction_following_elo_interval","value":7.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_instruction_following_elo","value":1241.6598929922711,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_instruction_following_elo_votes","value":18783,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_instruction_following_elo","value":1238.8405482188418,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_instruction_following_elo_votes","value":1233,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_instruction_following_elo_interval","value":16.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_instruction_following_elo","value":1236.1180965544263,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_instruction_following_elo_votes","value":2541,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_instruction_following_elo_interval","value":12.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_instruction_following_elo","value":1231.0824272694774,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_instruction_following_elo_votes","value":21910,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_instruction_following_elo","value":1222.6573838750105,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_instruction_following_elo_votes","value":2227,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_instruction_following_elo_interval","value":11.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_instruction_following_elo","value":1213.8090241126124,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_instruction_following_elo_votes","value":5485,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_instruction_following_elo_interval","value":8.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_instruction_following_elo","value":1205.8621758942948,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_instruction_following_elo_votes","value":29545,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_instruction_following_elo_interval","value":4.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_instruction_following_elo","value":1201.0835646252372,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_instruction_following_elo_votes","value":9162,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_instruction_following_elo_interval","value":6.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_instruction_following_elo","value":1196.5700618868048,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_instruction_following_elo_votes","value":4024,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_instruction_following_elo_interval","value":9.27,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_instruction_following_elo","value":1166.9211505717462,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_instruction_following_elo_votes","value":4153,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_instruction_following_elo_interval","value":9.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_instruction_following_elo","value":1158.8141282083452,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_instruction_following_elo_votes","value":19781,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_instruction_following_elo_interval","value":5.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_instruction_following_elo","value":1088.7506897449448,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_instruction_following_elo_votes","value":3171,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_instruction_following_elo_interval","value":10.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_instruction_following_elo","value":1030.9447364873354,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_instruction_following_elo_votes","value":3248,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_instruction_following_elo_interval","value":11.08,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_creative_writing_elo","value":1533.7003172605646,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_creative_writing_elo_votes","value":1945,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_creative_writing_elo_interval","value":15.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_creative_writing_elo","value":1526.9016494336047,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_creative_writing_elo_votes","value":1057,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_creative_writing_elo_interval","value":19.36,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_creative_writing_elo","value":1507.7499309795005,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_creative_writing_elo_votes","value":3284,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_creative_writing_elo_interval","value":11.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_creative_writing_elo","value":1504.86553125549,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_creative_writing_elo_votes","value":14950,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_creative_writing_elo_interval","value":6.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_creative_writing_elo","value":1494.1163340817186,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_creative_writing_elo_votes","value":9020,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_creative_writing_elo_interval","value":7.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_creative_writing_elo","value":1491.7159045056844,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_creative_writing_elo_votes","value":7375,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_creative_writing_elo_interval","value":8.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_creative_writing_elo","value":1491.5368053960146,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_creative_writing_elo_votes","value":8232,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_creative_writing_elo_interval","value":7.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_creative_writing_elo","value":1488.6782077218566,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_creative_writing_elo_votes","value":6003,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_creative_writing_elo_interval","value":8.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_creative_writing_elo","value":1486.985072854708,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_creative_writing_elo_votes","value":710,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_creative_writing_elo_interval","value":23.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_creative_writing_elo","value":1486.1501122544794,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_creative_writing_elo_votes","value":11806,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_creative_writing_elo_interval","value":6.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_creative_writing_elo","value":1482.1104969102923,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_creative_writing_elo_votes","value":23619,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_creative_writing_elo_interval","value":5.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_creative_writing_elo","value":1478.6267665151615,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_creative_writing_elo_votes","value":5471,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_creative_writing_elo_interval","value":8.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_creative_writing_elo","value":1469.826392019806,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_creative_writing_elo_votes","value":9481,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_creative_writing_elo_interval","value":7.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_creative_writing_elo","value":1466.8604297921613,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_creative_writing_elo_votes","value":1532,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_creative_writing_elo_interval","value":16.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_creative_writing_elo","value":1465.5447050716534,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_creative_writing_elo_votes","value":7583,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_creative_writing_elo_interval","value":7.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_creative_writing_elo","value":1465.049522177825,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_creative_writing_elo_votes","value":793,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_creative_writing_elo_interval","value":21.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_creative_writing_elo","value":1460.1885606039275,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_creative_writing_elo_votes","value":3844,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_creative_writing_elo_interval","value":10.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_creative_writing_elo","value":1455.5972818926136,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_creative_writing_elo_votes","value":6646,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_creative_writing_elo_interval","value":8.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_creative_writing_elo","value":1454.9553871119124,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_creative_writing_elo_votes","value":13156,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_creative_writing_elo_interval","value":6.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_creative_writing_elo","value":1454.2778794500719,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_creative_writing_elo_votes","value":12797,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_creative_writing_elo_interval","value":6.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_creative_writing_elo","value":1453.6320855418933,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_creative_writing_elo_votes","value":17694,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_creative_writing_elo_interval","value":5.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_creative_writing_elo","value":1453.507015795856,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_creative_writing_elo_votes","value":12259,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_creative_writing_elo_interval","value":6.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_creative_writing_elo","value":1449.0118397365527,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_creative_writing_elo_votes","value":8408,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_creative_writing_elo_interval","value":7.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_creative_writing_elo","value":1445.880260913334,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_creative_writing_elo_votes","value":9726,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_creative_writing_elo_interval","value":7.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_creative_writing_elo","value":1442.7107550843964,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_creative_writing_elo_votes","value":11412,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_creative_writing_elo_interval","value":6.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_creative_writing_elo","value":1441.8984142393372,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_creative_writing_elo_votes","value":8298,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_creative_writing_elo_interval","value":7.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_creative_writing_elo","value":1441.8636214527198,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_creative_writing_elo_votes","value":12416,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_creative_writing_elo_interval","value":5.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_creative_writing_elo","value":1441.170470054749,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_creative_writing_elo_votes","value":6983,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_creative_writing_elo_interval","value":8.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_creative_writing_elo","value":1439.7341695590244,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_creative_writing_elo_votes","value":1705,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_creative_writing_elo_interval","value":15.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_creative_writing_elo","value":1438.783684998781,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_creative_writing_elo_votes","value":11128,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_creative_writing_elo_interval","value":6.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_creative_writing_elo","value":1438.5585551953507,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_creative_writing_elo_votes","value":7841,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_creative_writing_elo_interval","value":7.6,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_creative_writing_elo","value":1438.4566946818743,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_creative_writing_elo_votes","value":14122,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_creative_writing_elo_interval","value":6.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_creative_writing_elo","value":1437.7598474851882,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_creative_writing_elo_votes","value":4852,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_creative_writing_elo_interval","value":8.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_creative_writing_elo","value":1435.3979018855298,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_creative_writing_elo_votes","value":12367,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_creative_writing_elo_interval","value":6.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_creative_writing_elo","value":1435.2956348814635,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_creative_writing_elo_votes","value":8948,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_creative_writing_elo_interval","value":7.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_creative_writing_elo","value":1433.4233851680228,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_creative_writing_elo_votes","value":6317,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_creative_writing_elo_interval","value":8.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_creative_writing_elo","value":1427.2448371254777,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_creative_writing_elo_votes","value":6246,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_creative_writing_elo_interval","value":8.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_creative_writing_elo","value":1426.8953978842815,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_creative_writing_elo_votes","value":6434,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_creative_writing_elo_interval","value":8.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_creative_writing_elo","value":1420.0644900066934,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_creative_writing_elo_votes","value":7473,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_creative_writing_elo_interval","value":7.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_creative_writing_elo","value":1417.5389006850462,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_creative_writing_elo_votes","value":1969,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_creative_writing_elo_interval","value":14.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_creative_writing_elo","value":1416.7676151862263,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_creative_writing_elo_votes","value":10285,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_creative_writing_elo_interval","value":7.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_creative_writing_elo","value":1415.4412211622218,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_creative_writing_elo_votes","value":974,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_creative_writing_elo_interval","value":18.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_creative_writing_elo","value":1412.0692929777667,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_creative_writing_elo_votes","value":9176,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_creative_writing_elo_interval","value":7.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_creative_writing_elo","value":1411.618163668568,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_creative_writing_elo_votes","value":5145,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_creative_writing_elo_interval","value":8.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_creative_writing_elo","value":1410.4756029952532,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_creative_writing_elo_votes","value":10875,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_creative_writing_elo_interval","value":6.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_creative_writing_elo","value":1406.3337529467906,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_creative_writing_elo_votes","value":1517,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_creative_writing_elo_interval","value":15.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_creative_writing_elo","value":1405.391680074165,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_creative_writing_elo_votes","value":2408,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_creative_writing_elo_interval","value":12.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_creative_writing_elo","value":1404.295223625462,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_creative_writing_elo_votes","value":11713,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_creative_writing_elo_interval","value":6.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_creative_writing_elo","value":1403.856116334883,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_creative_writing_elo_votes","value":7222,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_creative_writing_elo_interval","value":7.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_creative_writing_elo","value":1403.7281187000344,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_creative_writing_elo_votes","value":1665,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_creative_writing_elo_interval","value":14.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_creative_writing_elo","value":1403.2937377119658,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_creative_writing_elo_votes","value":8582,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_creative_writing_elo_interval","value":7.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_creative_writing_elo","value":1402.6583949915307,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_creative_writing_elo_votes","value":447,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_creative_writing_elo_interval","value":27.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_creative_writing_elo","value":1402.649685120453,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_creative_writing_elo_votes","value":2109,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_creative_writing_elo_interval","value":13.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_creative_writing_elo","value":1401.9609318013454,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_creative_writing_elo_votes","value":2429,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_creative_writing_elo_interval","value":12.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_creative_writing_elo","value":1401.7648212598167,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_creative_writing_elo_votes","value":16543,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_creative_writing_elo_interval","value":5.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_creative_writing_elo","value":1401.4517991698872,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_creative_writing_elo_votes","value":1001,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_creative_writing_elo_interval","value":18.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_creative_writing_elo","value":1401.2759519605345,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_creative_writing_elo_votes","value":10600,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_creative_writing_elo_interval","value":6.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_creative_writing_elo","value":1401.2527385909814,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_creative_writing_elo_votes","value":1960,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_creative_writing_elo_interval","value":13.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_creative_writing_elo","value":1399.9122738238252,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_creative_writing_elo_votes","value":17664,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_creative_writing_elo_interval","value":4.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_creative_writing_elo","value":1399.1924425825785,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_creative_writing_elo_votes","value":6883,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_creative_writing_elo_interval","value":7.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_creative_writing_elo","value":1396.1378234644778,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_creative_writing_elo_votes","value":8603,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_creative_writing_elo_interval","value":7.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_creative_writing_elo","value":1394.9136621393448,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_creative_writing_elo_votes","value":3093,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_creative_writing_elo_interval","value":10.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_creative_writing_elo","value":1393.1746693373316,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_creative_writing_elo_votes","value":7900,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_creative_writing_elo_interval","value":7.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_creative_writing_elo","value":1387.2357516114084,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_creative_writing_elo_votes","value":8748,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_creative_writing_elo_interval","value":7.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_creative_writing_elo","value":1386.6925847091948,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_creative_writing_elo_votes","value":2589,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_creative_writing_elo_interval","value":12.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_creative_writing_elo","value":1384.228302708541,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_creative_writing_elo_votes","value":4668,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_creative_writing_elo_interval","value":9.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_creative_writing_elo","value":1383.558640322074,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_creative_writing_elo_votes","value":1084,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_creative_writing_elo_interval","value":17.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_creative_writing_elo","value":1379.7547576223847,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_creative_writing_elo_votes","value":13226,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_creative_writing_elo_interval","value":6.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_creative_writing_elo","value":1375.7722791539572,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_creative_writing_elo_votes","value":7660,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_creative_writing_elo_interval","value":7.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_creative_writing_elo","value":1374.803855805403,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_creative_writing_elo_votes","value":13895,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_creative_writing_elo_interval","value":5.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_creative_writing_elo","value":1373.8925923780791,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_creative_writing_elo_votes","value":2073,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_creative_writing_elo_interval","value":13.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_creative_writing_elo","value":1371.2958089109152,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_creative_writing_elo_votes","value":25394,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_creative_writing_elo_interval","value":4.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_creative_writing_elo","value":1370.2125686889717,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_creative_writing_elo_votes","value":10818,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_creative_writing_elo_interval","value":6.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_creative_writing_elo","value":1367.8089898606893,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_creative_writing_elo_votes","value":4521,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_creative_writing_elo_interval","value":9.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_creative_writing_elo","value":1366.067785255858,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_creative_writing_elo_votes","value":1356,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_creative_writing_elo_interval","value":16.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_creative_writing_elo","value":1365.2240808768222,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_creative_writing_elo_votes","value":4015,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_creative_writing_elo_interval","value":9.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_creative_writing_elo","value":1364.018841630652,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_creative_writing_elo_votes","value":5990,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_creative_writing_elo_interval","value":7.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_creative_writing_elo","value":1363.4814495122112,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_creative_writing_elo_votes","value":6650,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_creative_writing_elo_interval","value":7.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_creative_writing_elo","value":1362.1121978718147,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_creative_writing_elo_votes","value":4298,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_creative_writing_elo_interval","value":9.36,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_creative_writing_elo","value":1361.9471103002904,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_creative_writing_elo_votes","value":1694,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_creative_writing_elo_interval","value":15.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_creative_writing_elo","value":1358.5338434567034,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_creative_writing_elo_votes","value":7636,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_creative_writing_elo_interval","value":7.27,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_creative_writing_elo","value":1356.8033280584798,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_creative_writing_elo_votes","value":9775,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_creative_writing_elo_interval","value":6.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_creative_writing_elo","value":1354.0624670606803,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_creative_writing_elo_votes","value":14495,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_creative_writing_elo_interval","value":6.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_creative_writing_elo","value":1347.6066190400584,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_creative_writing_elo_votes","value":4680,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_creative_writing_elo_interval","value":8.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_creative_writing_elo","value":1347.3203528921363,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_creative_writing_elo_votes","value":4642,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_creative_writing_elo_interval","value":9.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_creative_writing_elo","value":1347.2168081482293,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_creative_writing_elo_votes","value":424,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_creative_writing_elo_interval","value":28.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_creative_writing_elo","value":1345.490724765471,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_creative_writing_elo_votes","value":6308,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_creative_writing_elo_interval","value":7.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_creative_writing_elo","value":1343.2873091699084,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_creative_writing_elo_votes","value":3999,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_creative_writing_elo_interval","value":9.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_creative_writing_elo","value":1343.1522788308146,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_creative_writing_elo_votes","value":9752,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_creative_writing_elo_interval","value":6.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_creative_writing_elo","value":1333.3717386363933,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_creative_writing_elo_votes","value":3033,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_creative_writing_elo_interval","value":10.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_creative_writing_elo","value":1333.0664420163944,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_creative_writing_elo_votes","value":3239,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_creative_writing_elo_interval","value":10.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_creative_writing_elo","value":1331.1956688976493,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_creative_writing_elo_votes","value":600,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_creative_writing_elo_interval","value":23.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_creative_writing_elo","value":1331.1951199827358,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_creative_writing_elo_votes","value":6963,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_creative_writing_elo_interval","value":8.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_creative_writing_elo","value":1330.148202303706,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_creative_writing_elo_votes","value":6671,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_creative_writing_elo_interval","value":7.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_creative_writing_elo","value":1325.288636391021,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_creative_writing_elo_votes","value":3520,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_creative_writing_elo_interval","value":10.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_creative_writing_elo","value":1319.184525750984,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_creative_writing_elo_votes","value":7602,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_creative_writing_elo_interval","value":7.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_creative_writing_elo","value":1317.242119752354,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_creative_writing_elo_votes","value":2964,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_creative_writing_elo_interval","value":10.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_creative_writing_elo","value":1317.189047215376,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_creative_writing_elo_votes","value":1121,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_creative_writing_elo_interval","value":17.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_creative_writing_elo","value":1314.5303531232057,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_creative_writing_elo_votes","value":1775,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_creative_writing_elo_interval","value":14.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_creative_writing_elo","value":1314.1790976011469,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_creative_writing_elo_votes","value":10371,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_creative_writing_elo_interval","value":7.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_creative_writing_elo","value":1313.631573314569,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_creative_writing_elo_votes","value":4615,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_creative_writing_elo_interval","value":9.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_creative_writing_elo","value":1307.6456644003174,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_creative_writing_elo_votes","value":4748,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_creative_writing_elo_interval","value":9.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_creative_writing_elo","value":1299.441388670851,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_creative_writing_elo_votes","value":5082,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_creative_writing_elo_interval","value":8.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_creative_writing_elo","value":1297.4857150695748,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_creative_writing_elo_votes","value":4502,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_creative_writing_elo_interval","value":9.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_creative_writing_elo","value":1297.1476949097537,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_creative_writing_elo_votes","value":616,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_creative_writing_elo_interval","value":22.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_creative_writing_elo","value":1295.6525497341484,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_creative_writing_elo_votes","value":1873,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_creative_writing_elo_interval","value":13.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_creative_writing_elo","value":1294.5407922919178,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_creative_writing_elo_votes","value":614,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_creative_writing_elo_interval","value":22.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_creative_writing_elo","value":1293.9543615698449,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_creative_writing_elo_votes","value":5786,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_creative_writing_elo_interval","value":8.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_creative_writing_elo","value":1291.7554943178059,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_creative_writing_elo_votes","value":1763,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_creative_writing_elo_interval","value":14.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_creative_writing_elo","value":1291.3084955231466,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_creative_writing_elo_votes","value":16599,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_creative_writing_elo_interval","value":7.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_creative_writing_elo","value":1288.6816419483287,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_creative_writing_elo_votes","value":547,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_creative_writing_elo_interval","value":25.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_creative_writing_elo","value":1285.9383381759553,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_creative_writing_elo_votes","value":897,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_creative_writing_elo_interval","value":20.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_creative_writing_elo","value":1285.6865636444516,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_creative_writing_elo_votes","value":3065,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_creative_writing_elo_interval","value":10.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_creative_writing_elo","value":1274.8022546204484,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_creative_writing_elo_votes","value":3908,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_creative_writing_elo_interval","value":9.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_creative_writing_elo","value":1274.4292292871608,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_creative_writing_elo_votes","value":6756,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_creative_writing_elo_interval","value":8.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_creative_writing_elo","value":1272.8322618070497,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_creative_writing_elo_votes","value":8163,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_creative_writing_elo_interval","value":6.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_creative_writing_elo","value":1271.447461118194,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_creative_writing_elo_votes","value":3340,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_creative_writing_elo_interval","value":10.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_creative_writing_elo","value":1270.3087897084351,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_creative_writing_elo_votes","value":666,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_creative_writing_elo_interval","value":21.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_creative_writing_elo","value":1267.6532032313792,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_creative_writing_elo_votes","value":10486,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_creative_writing_elo_interval","value":6.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_creative_writing_elo","value":1266.224863749421,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_creative_writing_elo_votes","value":5151,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_creative_writing_elo_interval","value":8.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_creative_writing_elo","value":1259.9641047770426,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_creative_writing_elo_votes","value":1005,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_creative_writing_elo_interval","value":18.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_creative_writing_elo","value":1252.2101093704227,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_creative_writing_elo_votes","value":4113,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_creative_writing_elo_interval","value":9.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_creative_writing_elo","value":1250.232554893343,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_creative_writing_elo_votes","value":8046,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_creative_writing_elo_interval","value":7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_creative_writing_elo","value":1249.4427744132367,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_creative_writing_elo_votes","value":911,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_creative_writing_elo_interval","value":19.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_creative_writing_elo","value":1248.6628835439574,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_creative_writing_elo_votes","value":3760,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_creative_writing_elo_interval","value":10,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_creative_writing_elo","value":1242.6768309413437,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_creative_writing_elo_votes","value":6692,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_creative_writing_elo_interval","value":8.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_creative_writing_elo","value":1240.4873261764933,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_creative_writing_elo_votes","value":11429,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_creative_writing_elo_interval","value":6.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_creative_writing_elo","value":1236.2954049421621,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_creative_writing_elo_votes","value":628,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_creative_writing_elo_interval","value":26.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_creative_writing_elo","value":1234.5285472634987,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_creative_writing_elo_votes","value":1474,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_creative_writing_elo_interval","value":15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_creative_writing_elo","value":1231.7264219420892,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_creative_writing_elo_votes","value":8250,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_creative_writing_elo_interval","value":7.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_creative_writing_elo","value":1221.117436419867,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_creative_writing_elo_votes","value":5684,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_creative_writing_elo_interval","value":8.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_creative_writing_elo","value":1201.0912840896099,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_creative_writing_elo_votes","value":1234,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_creative_writing_elo_interval","value":17.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_creative_writing_elo","value":1194.5428719864385,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_creative_writing_elo_votes","value":2415,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_creative_writing_elo_interval","value":12.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_creative_writing_elo","value":1181.4584916428857,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_creative_writing_elo_votes","value":4062,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_creative_writing_elo_interval","value":9.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_creative_writing_elo","value":1173.7570176854824,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_creative_writing_elo_votes","value":836,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_creative_writing_elo_interval","value":19.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_creative_writing_elo","value":1169.758281737067,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_creative_writing_elo_votes","value":1421,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_creative_writing_elo_interval","value":15.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_creative_writing_elo","value":1154.1647133226754,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_creative_writing_elo_votes","value":7346,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_creative_writing_elo_interval","value":8.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_creative_writing_elo","value":1094.0266267755749,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_creative_writing_elo_votes","value":1070,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_creative_writing_elo_interval","value":18.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_creative_writing_elo","value":1032.634024174343,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_creative_writing_elo_votes","value":1091,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_creative_writing_elo_interval","value":19.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_vision_elo","value":1324.8788723175815,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_vision_elo_votes","value":14714,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_vision_elo_interval","value":7.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_vision_elo","value":1320.823800046,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_vision_elo_votes","value":3035,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_vision_elo_interval","value":11.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_vision_elo","value":1319.623943187484,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_vision_elo_votes","value":17743,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_vision_elo_interval","value":6.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_vision_elo","value":1319.4899087995987,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_vision_elo_votes","value":5026,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_vision_elo_interval","value":9.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_vision_elo","value":1316.9363635860252,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_vision_elo_votes","value":23139,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_vision_elo_interval","value":6.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_vision_elo","value":1315.6723027974679,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_vision_elo_votes","value":22286,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_vision_elo_interval","value":6.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_vision_elo","value":1315.379362654793,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_vision_elo_votes","value":4645,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_vision_elo_interval","value":9.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_vision_elo","value":1314.2261159913364,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_vision_elo_votes","value":5369,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_vision_elo_interval","value":9.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_vision_elo","value":1312.935382439709,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_vision_elo_votes","value":9957,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_vision_elo_interval","value":7.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_vision_elo","value":1308.414166200037,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_vision_elo_votes","value":5392,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_vision_elo_interval","value":9.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_vision_elo","value":1308.32534406439,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_vision_elo_votes","value":13862,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_vision_elo_interval","value":6.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_vision_elo","value":1304.2153267211183,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_vision_elo_votes","value":1948,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_vision_elo_interval","value":14.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_vision_elo","value":1302.6274518457858,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_vision_elo_votes","value":30747,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_vision_elo_interval","value":5.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_vision_elo","value":1298.8770393167063,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_vision_elo_votes","value":8979,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_vision_elo_interval","value":7.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_vision_elo","value":1296.996303119526,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_vision_elo_votes","value":28781,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_vision_elo_interval","value":5.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_vision_elo","value":1295.7822786391075,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_vision_elo_votes","value":47114,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_vision_elo_interval","value":5.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_vision_elo","value":1294.491387370161,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_vision_elo_votes","value":18303,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_vision_elo_interval","value":6.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_vision_elo","value":1293.8678100737243,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_vision_elo_votes","value":16254,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_vision_elo_interval","value":6.36,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_vision_elo","value":1292.5016810249715,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_vision_elo_votes","value":12804,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_vision_elo_interval","value":6.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6.1-sol","source":"arena","metric":"arena_vision_elo","value":1287.7313467775475,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6.1-sol","source":"arena","metric":"arena_vision_elo_votes","value":2330,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6.1-sol","source":"arena","metric":"arena_vision_elo_interval","value":12.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_vision_elo","value":1287.21834956692,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_vision_elo_votes","value":2564,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_vision_elo_interval","value":12.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_vision_elo","value":1287.1225634879884,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_vision_elo_votes","value":12599,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_vision_elo_interval","value":7.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_vision_elo","value":1282.7633262406994,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_vision_elo_votes","value":27408,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_vision_elo_interval","value":6.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_vision_elo","value":1282.1119761531568,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_vision_elo_votes","value":16368,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_vision_elo_interval","value":6.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_vision_elo","value":1280.6177272297055,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_vision_elo_votes","value":11439,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_vision_elo_interval","value":7.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-astra","source":"arena","metric":"arena_vision_elo","value":1279.8986527925117,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-astra","source":"arena","metric":"arena_vision_elo_votes","value":4012,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-astra","source":"arena","metric":"arena_vision_elo_interval","value":10.27,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_vision_elo","value":1278.1470332728204,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_vision_elo_votes","value":14212,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_vision_elo_interval","value":6.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"arena","metric":"arena_vision_elo","value":1277.8593561291239,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"arena","metric":"arena_vision_elo_votes","value":4100,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"arena","metric":"arena_vision_elo_interval","value":10.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_vision_elo","value":1276.471135628896,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_vision_elo_votes","value":40219,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_vision_elo_interval","value":5.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_vision_elo","value":1272.5476789147583,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_vision_elo_votes","value":14034,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_vision_elo_interval","value":6.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_vision_elo","value":1272.171620981572,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_vision_elo_votes","value":1008,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_vision_elo_interval","value":19.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_vision_elo","value":1270.9741940618744,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_vision_elo_votes","value":11842,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_vision_elo_interval","value":7.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_vision_elo","value":1269.463029799551,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_vision_elo_votes","value":7614,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_vision_elo_interval","value":8.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_vision_elo","value":1269.067499973593,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_vision_elo_votes","value":9238,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_vision_elo_interval","value":7.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_vision_elo","value":1269.0200631630391,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_vision_elo_votes","value":28249,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_vision_elo_interval","value":5.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_vision_elo","value":1264.584469224122,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_vision_elo_votes","value":1649,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_vision_elo_interval","value":15.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_vision_elo","value":1263.9092869157691,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_vision_elo_votes","value":42757,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_vision_elo_interval","value":5.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_vision_elo","value":1263.3321928931312,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_vision_elo_votes","value":88755,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_vision_elo_interval","value":4.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_vision_elo","value":1263.0068980770138,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_vision_elo_votes","value":7261,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_vision_elo_interval","value":8.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_vision_elo","value":1262.8399732080727,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_vision_elo_votes","value":1754,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_vision_elo_interval","value":14.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_vision_elo","value":1262.4660916015766,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_vision_elo_votes","value":32657,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_vision_elo_interval","value":5.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_vision_elo","value":1259.550227985578,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_vision_elo_votes","value":23922,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_vision_elo_interval","value":6.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_vision_elo","value":1257.1473899499424,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_vision_elo_votes","value":11055,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_vision_elo_interval","value":7.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_vision_elo","value":1255.7442227458723,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_vision_elo_votes","value":3618,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_vision_elo_interval","value":10.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_vision_elo","value":1251.0548647162113,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_vision_elo_votes","value":19844,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_vision_elo_interval","value":6.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_vision_elo","value":1249.5112060955219,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_vision_elo_votes","value":9848,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_vision_elo_interval","value":7.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_vision_elo","value":1247.0433261116336,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_vision_elo_votes","value":29381,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_vision_elo_interval","value":5.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_vision_elo","value":1246.9892089993264,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_vision_elo_votes","value":12724,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_vision_elo_interval","value":6.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_vision_elo","value":1245.7853715616577,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_vision_elo_votes","value":19022,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_vision_elo_interval","value":6.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_vision_elo","value":1244.8170157186942,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_vision_elo_votes","value":25734,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_vision_elo_interval","value":6.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_vision_elo","value":1244.4983243612196,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_vision_elo_votes","value":13236,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_vision_elo_interval","value":6.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_vision_elo","value":1241.0169654688623,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_vision_elo_votes","value":30272,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_vision_elo_interval","value":5.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_vision_elo","value":1240.1779210359143,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_vision_elo_votes","value":27657,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_vision_elo_interval","value":5.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-sol","source":"arena","metric":"arena_vision_elo","value":1239.9451140020133,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-sol","source":"arena","metric":"arena_vision_elo_votes","value":3221,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-sol","source":"arena","metric":"arena_vision_elo_interval","value":11.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_vision_elo","value":1236.796377631557,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_vision_elo_votes","value":8074,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_vision_elo_interval","value":8.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_vision_elo","value":1235.476708760441,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_vision_elo_votes","value":60087,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_vision_elo_interval","value":4.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_vision_elo","value":1232.1875376313596,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_vision_elo_votes","value":39894,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_vision_elo_interval","value":7.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_vision_elo","value":1230.957267472956,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_vision_elo_votes","value":3736,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_vision_elo_interval","value":10.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_vision_elo","value":1229.283685177617,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_vision_elo_votes","value":27901,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_vision_elo_interval","value":5.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_vision_elo","value":1222.4523372948931,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_vision_elo_votes","value":5375,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_vision_elo_interval","value":9.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-luna","source":"arena","metric":"arena_vision_elo","value":1216.103808862197,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-luna","source":"arena","metric":"arena_vision_elo_votes","value":3662,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-luna","source":"arena","metric":"arena_vision_elo_interval","value":10.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o3","source":"arena","metric":"arena_vision_elo","value":1214.3017183965094,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o3","source":"arena","metric":"arena_vision_elo_votes","value":45567,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o3","source":"arena","metric":"arena_vision_elo_interval","value":6.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_vision_elo","value":1210.427481255077,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_vision_elo_votes","value":40998,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_vision_elo_interval","value":6.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_vision_elo","value":1202.226332986973,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_vision_elo_votes","value":28943,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_vision_elo_interval","value":7.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_vision_elo","value":1195.6011013077389,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_vision_elo_votes","value":25624,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_vision_elo_interval","value":6.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_vision_elo","value":1194.0123876044438,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_vision_elo_votes","value":41316,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_vision_elo_interval","value":7.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_vision_elo","value":1181.412382204995,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_vision_elo_votes","value":40201,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_vision_elo_interval","value":7.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3.1","source":"arena","metric":"arena_vision_elo","value":1172.227170828708,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3.1","source":"arena","metric":"arena_vision_elo_votes","value":41611,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3.1","source":"arena","metric":"arena_vision_elo_interval","value":6.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o1","source":"arena","metric":"arena_vision_elo","value":1168.371030308677,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o1","source":"arena","metric":"arena_vision_elo_votes","value":3694,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o1","source":"arena","metric":"arena_vision_elo_interval","value":10.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_vision_elo","value":1164.5475341760637,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_vision_elo_votes","value":16982,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_vision_elo_interval","value":8.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_vision_elo","value":1163.9380369890487,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_vision_elo_votes","value":2455,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_vision_elo_interval","value":13.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_vision_elo","value":1159.4544819902562,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_vision_elo_votes","value":3928,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_vision_elo_interval","value":11.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3","source":"arena","metric":"arena_vision_elo","value":1157.0063068644836,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3","source":"arena","metric":"arena_vision_elo_votes","value":10793,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3","source":"arena","metric":"arena_vision_elo_interval","value":8.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_vision_elo","value":1154.4119985498196,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_vision_elo_votes","value":3243,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_vision_elo_interval","value":11.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_vision_elo","value":1141.7080159614773,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_vision_elo_votes","value":6923,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_vision_elo_interval","value":9.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_vision_elo","value":1136.635611496261,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_vision_elo_votes","value":23273,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_vision_elo_interval","value":8.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_vision_elo","value":1136.4712697816929,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_vision_elo_votes","value":28490,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_vision_elo_interval","value":8.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_vision_elo","value":1118.3570237168362,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_vision_elo_votes","value":6446,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_vision_elo_interval","value":9.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen2.5-vl-72b-instruct","source":"arena","metric":"arena_vision_elo","value":1107.3900594968854,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen2.5-vl-72b-instruct","source":"arena","metric":"arena_vision_elo_votes","value":3768,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen2.5-vl-72b-instruct","source":"arena","metric":"arena_vision_elo_interval","value":10.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4-turbo","source":"arena","metric":"arena_vision_elo","value":1089.8779178737723,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4-turbo","source":"arena","metric":"arena_vision_elo_votes","value":13391,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4-turbo","source":"arena","metric":"arena_vision_elo_interval","value":11.6,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_vision_elo","value":1065.6313069345274,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_vision_elo_votes","value":17341,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_vision_elo_interval","value":8.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_vision_elo","value":1064.564991850618,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_vision_elo_votes","value":3376,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_vision_elo_interval","value":12.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_vision_elo","value":1063.2309556256519,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_vision_elo_votes","value":1211,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_vision_elo_interval","value":18.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"amazon/nova-lite-v1","source":"arena","metric":"arena_vision_elo","value":990.448672519729,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"amazon/nova-lite-v1","source":"arena","metric":"arena_vision_elo_votes","value":1854,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"amazon/nova-lite-v1","source":"arena","metric":"arena_vision_elo_interval","value":15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"amazon/nova-pro-v1","source":"arena","metric":"arena_vision_elo","value":980.4564281493098,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"amazon/nova-pro-v1","source":"arena","metric":"arena_vision_elo_votes","value":2335,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"amazon/nova-pro-v1","source":"arena","metric":"arena_vision_elo_interval","value":13.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_english_elo","value":1537.673544921211,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_english_elo_votes","value":1902,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_english_elo_interval","value":13.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_english_elo","value":1516.9135117399276,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_english_elo_votes","value":3165,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_english_elo_interval","value":11.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_english_elo","value":1512.0357536247232,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_english_elo_votes","value":35808,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_english_elo_interval","value":4.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_english_elo","value":1509.4143646757998,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_english_elo_votes","value":1326,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_english_elo_interval","value":16.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_english_elo","value":1507.3117615285585,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_english_elo_votes","value":13105,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_english_elo_interval","value":6.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_english_elo","value":1504.9256599499006,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_english_elo_votes","value":5935,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_english_elo_interval","value":8.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_english_elo","value":1503.9402904855274,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_english_elo_votes","value":1503,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_english_elo_interval","value":14.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_english_elo","value":1499.0022210011568,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_english_elo_votes","value":14771,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_english_elo_interval","value":6.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_english_elo","value":1498.9858012996613,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_english_elo_votes","value":17924,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_english_elo_interval","value":5.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_english_elo","value":1496.2835289330583,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_english_elo_votes","value":30177,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_english_elo_interval","value":4.89,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_english_elo","value":1493.1582826480308,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_english_elo_votes","value":6959,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_english_elo_interval","value":7.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_english_elo","value":1491.9854510984003,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_english_elo_votes","value":10584,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_english_elo_interval","value":6.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_english_elo","value":1484.526481205052,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_english_elo_votes","value":2578,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_english_elo_interval","value":12.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_english_elo","value":1484.0055684156898,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_english_elo_votes","value":3309,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_english_elo_interval","value":10.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_english_elo","value":1483.2364388870556,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_english_elo_votes","value":10911,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_english_elo_interval","value":6.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_english_elo","value":1481.673713095701,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_english_elo_votes","value":15173,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_english_elo_interval","value":5.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_english_elo","value":1481.306992445245,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_english_elo_votes","value":12464,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_english_elo_interval","value":6.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_english_elo","value":1480.5176594484094,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_english_elo_votes","value":20571,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_english_elo_interval","value":5.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_english_elo","value":1478.2563274799727,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_english_elo_votes","value":56117,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_english_elo_interval","value":3.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_english_elo","value":1477.7529376046411,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_english_elo_votes","value":17382,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_english_elo_interval","value":5.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_english_elo","value":1477.3791648455403,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_english_elo_votes","value":4034,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_english_elo_interval","value":9.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_english_elo","value":1477.2362203262055,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_english_elo_votes","value":31715,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_english_elo_interval","value":4.6,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_english_elo","value":1475.077533930148,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_english_elo_votes","value":26947,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_english_elo_interval","value":4.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_english_elo","value":1474.4591814164944,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_english_elo_votes","value":12160,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_english_elo_interval","value":6.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_english_elo","value":1472.403005393508,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_english_elo_votes","value":31965,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_english_elo_interval","value":4.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_english_elo","value":1470.3358526049658,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_english_elo_votes","value":31558,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_english_elo_interval","value":4.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_english_elo","value":1468.599541183802,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_english_elo_votes","value":28033,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_english_elo_interval","value":4.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_english_elo","value":1466.8367450544351,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_english_elo_votes","value":29330,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_english_elo_interval","value":4.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_english_elo","value":1460.627235681021,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_english_elo_votes","value":31213,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_english_elo_interval","value":4.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_english_elo","value":1460.1719643390172,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_english_elo_votes","value":18161,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_english_elo_interval","value":5.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_english_elo","value":1459.340492234993,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_english_elo_votes","value":25292,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_english_elo_interval","value":5.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_english_elo","value":1458.734105788767,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_english_elo_votes","value":17716,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_english_elo_interval","value":5.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_english_elo","value":1458.0963988695266,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_english_elo_votes","value":54059,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_english_elo_interval","value":3.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_english_elo","value":1457.9545071998773,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_english_elo_votes","value":16314,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_english_elo_interval","value":5.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_english_elo","value":1457.5819093113498,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_english_elo_votes","value":12922,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_english_elo_interval","value":5.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_english_elo","value":1453.7809586305234,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_english_elo_votes","value":4453,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_english_elo_interval","value":8.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_english_elo","value":1453.0394412401056,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_english_elo_votes","value":5027,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_english_elo_interval","value":8.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_english_elo","value":1453.0093691747609,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_english_elo_votes","value":16197,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_english_elo_interval","value":5.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_english_elo","value":1451.0114732464142,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_english_elo_votes","value":2332,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_english_elo_interval","value":11.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_english_elo","value":1450.8918734084311,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_english_elo_votes","value":16710,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_english_elo_interval","value":5.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_english_elo","value":1450.1354957988556,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_english_elo_votes","value":20842,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_english_elo_interval","value":5.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_english_elo","value":1450.0398644996144,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_english_elo_votes","value":35731,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_english_elo_interval","value":3.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_english_elo","value":1448.8514170035146,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_english_elo_votes","value":2521,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_english_elo_interval","value":11.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_english_elo","value":1448.8327796288256,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_english_elo_votes","value":15323,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_english_elo_interval","value":5.36,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_english_elo","value":1448.2307129424312,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_english_elo_votes","value":17561,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_english_elo_interval","value":5.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_english_elo","value":1447.4800052891392,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_english_elo_votes","value":8818,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_english_elo_interval","value":6.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_english_elo","value":1447.3412941516635,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_english_elo_votes","value":4659,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_english_elo_interval","value":8.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_english_elo","value":1447.0304765087606,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_english_elo_votes","value":21370,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_english_elo_interval","value":5.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_english_elo","value":1445.3753360538783,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_english_elo_votes","value":21614,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_english_elo_interval","value":5.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_english_elo","value":1443.911986023498,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_english_elo_votes","value":2249,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_english_elo_interval","value":11.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_english_elo","value":1443.79796058119,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_english_elo_votes","value":26416,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_english_elo_interval","value":4.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_english_elo","value":1443.272784173687,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_english_elo_votes","value":41306,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_english_elo_interval","value":4.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_english_elo","value":1442.2979491013434,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_english_elo_votes","value":16677,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_english_elo_interval","value":5.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_english_elo","value":1441.3675281934554,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_english_elo_votes","value":16656,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_english_elo_interval","value":5.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_english_elo","value":1440.7905090834136,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_english_elo_votes","value":23129,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_english_elo_interval","value":5.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_english_elo","value":1440.228692300254,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_english_elo_votes","value":5047,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_english_elo_interval","value":8.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_english_elo","value":1437.9107584634864,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_english_elo_votes","value":14626,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_english_elo_interval","value":5.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_english_elo","value":1437.1400505862493,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_english_elo_votes","value":8163,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_english_elo_interval","value":7.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_english_elo","value":1436.696597032956,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_english_elo_votes","value":19617,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_english_elo_interval","value":5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_english_elo","value":1436.5205835290344,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_english_elo_votes","value":10120,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_english_elo_interval","value":6.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_english_elo","value":1433.1992284516396,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_english_elo_votes","value":5651,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_english_elo_interval","value":8.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_english_elo","value":1432.537197337071,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_english_elo_votes","value":11735,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_english_elo_interval","value":6.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_english_elo","value":1431.8632215050893,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_english_elo_votes","value":2970,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_english_elo_interval","value":10.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_english_elo","value":1429.2864724751335,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_english_elo_votes","value":3901,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_english_elo_interval","value":9.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_english_elo","value":1429.0666949369552,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_english_elo_votes","value":4932,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_english_elo_interval","value":9.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_english_elo","value":1428.524829667069,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_english_elo_votes","value":13158,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_english_elo_interval","value":5.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_english_elo","value":1426.4829772594376,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_english_elo_votes","value":32163,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_english_elo_interval","value":4.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_english_elo","value":1426.1456715882023,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_english_elo_votes","value":35157,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_english_elo_interval","value":4.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_english_elo","value":1424.8721505092699,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_english_elo_votes","value":12753,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_english_elo_interval","value":5.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_english_elo","value":1423.8483158113822,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_english_elo_votes","value":41055,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_english_elo_interval","value":3.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_english_elo","value":1422.314852558372,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_english_elo_votes","value":21224,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_english_elo_interval","value":4.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_english_elo","value":1421.3272606804592,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_english_elo_votes","value":9735,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_english_elo_interval","value":6.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_english_elo","value":1421.19313328287,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_english_elo_votes","value":13225,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_english_elo_interval","value":6.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_english_elo","value":1418.9545031761331,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_english_elo_votes","value":1580,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_english_elo_interval","value":14.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_english_elo","value":1417.7334570382543,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_english_elo_votes","value":54705,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_english_elo_interval","value":3.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_english_elo","value":1417.26868742749,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_english_elo_votes","value":25256,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_english_elo_interval","value":4.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_english_elo","value":1416.4404328017304,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_english_elo_votes","value":27283,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_english_elo_interval","value":4.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_english_elo","value":1414.376227006132,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_english_elo_votes","value":8526,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_english_elo_interval","value":7.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_english_elo","value":1413.8907069367474,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_english_elo_votes","value":64734,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_english_elo_interval","value":3.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_english_elo","value":1413.820671255704,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_english_elo_votes","value":29500,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_english_elo_interval","value":4.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_english_elo","value":1412.2722028219896,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_english_elo_votes","value":4571,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_english_elo_interval","value":9.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_english_elo","value":1411.7307164248805,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_english_elo_votes","value":29159,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_english_elo_interval","value":4.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_english_elo","value":1409.0823320866018,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_english_elo_votes","value":13606,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_english_elo_interval","value":5.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_english_elo","value":1406.8668573464315,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_english_elo_votes","value":13568,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_english_elo_interval","value":5.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_english_elo","value":1404.4673808225498,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_english_elo_votes","value":26631,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_english_elo_interval","value":4.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_english_elo","value":1404.0985567745229,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_english_elo_votes","value":32785,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_english_elo_interval","value":4.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_english_elo","value":1400.666894157543,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_english_elo_votes","value":3160,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_english_elo_interval","value":10.27,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_english_elo","value":1397.4346926717626,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_english_elo_votes","value":13218,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_english_elo_interval","value":5.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_english_elo","value":1394.6224204398557,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_english_elo_votes","value":1169,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_english_elo_interval","value":16.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_english_elo","value":1392.337342931672,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_english_elo_votes","value":23360,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_english_elo_interval","value":4.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_english_elo","value":1392.2432355794963,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_english_elo_votes","value":5903,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_english_elo_interval","value":7.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_english_elo","value":1391.1520529684667,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_english_elo_votes","value":9759,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_english_elo_interval","value":6.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_english_elo","value":1388.9158456244033,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_english_elo_votes","value":21422,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_english_elo_interval","value":4.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_english_elo","value":1384.5665935358354,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_english_elo_votes","value":5157,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_english_elo_interval","value":8.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_english_elo","value":1381.008867302312,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_english_elo_votes","value":28906,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_english_elo_interval","value":4.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_english_elo","value":1379.9397739965939,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_english_elo_votes","value":18780,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_english_elo_interval","value":5.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_english_elo","value":1378.786916125759,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_english_elo_votes","value":1208,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_english_elo_interval","value":16.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_english_elo","value":1378.7353139798638,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_english_elo_votes","value":11472,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_english_elo_interval","value":6.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_english_elo","value":1376.545223050502,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_english_elo_votes","value":23044,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_english_elo_interval","value":4.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_english_elo","value":1374.6211187116498,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_english_elo_votes","value":13030,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_english_elo_interval","value":5.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_english_elo","value":1372.6897809097145,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_english_elo_votes","value":4652,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_english_elo_interval","value":8.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_english_elo","value":1372.1552768834988,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_english_elo_votes","value":16316,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_english_elo_interval","value":5.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_english_elo","value":1367.419515346665,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_english_elo_votes","value":20833,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_english_elo_interval","value":5.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_english_elo","value":1363.684901626402,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_english_elo_votes","value":2998,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_english_elo_interval","value":10.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_english_elo","value":1363.032441189134,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_english_elo_votes","value":14945,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_english_elo_interval","value":5.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_english_elo","value":1362.3200447685872,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_english_elo_votes","value":2025,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_english_elo_interval","value":12.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_english_elo","value":1359.4894567658691,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_english_elo_votes","value":10980,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_english_elo_interval","value":6.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_english_elo","value":1359.0540143974,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_english_elo_votes","value":2230,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_english_elo_interval","value":12.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_english_elo","value":1356.010189342183,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_english_elo_votes","value":14365,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_english_elo_interval","value":6.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_english_elo","value":1355.7985513314147,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_english_elo_votes","value":18060,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_english_elo_interval","value":5.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_english_elo","value":1351.035155182516,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_english_elo_votes","value":11130,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_english_elo_interval","value":6.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_english_elo","value":1348.4613542299237,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_english_elo_votes","value":2330,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_english_elo_interval","value":11.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_english_elo","value":1343.5670353813482,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_english_elo_votes","value":26256,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_english_elo_interval","value":4.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_english_elo","value":1337.5771754828493,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_english_elo_votes","value":1412,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_english_elo_interval","value":16.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_english_elo","value":1334.6060759858012,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_english_elo_votes","value":12316,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_english_elo_interval","value":6.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_english_elo","value":1333.111441784589,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_english_elo_votes","value":28651,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_english_elo_interval","value":4.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_english_elo","value":1321.5264974296063,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_english_elo_votes","value":3580,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_english_elo_interval","value":9.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_english_elo","value":1312.2979532260906,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_english_elo_votes","value":60226,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_english_elo_interval","value":4.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_english_elo","value":1304.2310677981648,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_english_elo_votes","value":13040,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_english_elo_interval","value":6.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_english_elo","value":1303.349283850632,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_english_elo_votes","value":29253,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_english_elo_interval","value":4.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_english_elo","value":1303.1780149797005,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_english_elo_votes","value":3528,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_english_elo_interval","value":9.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_english_elo","value":1302.9193155920793,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_english_elo_votes","value":4514,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_english_elo_interval","value":9.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_english_elo","value":1302.497053902076,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_english_elo_votes","value":18917,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_english_elo_interval","value":5.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_english_elo","value":1300.5211577825492,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_english_elo_votes","value":37735,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_english_elo_interval","value":4.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_english_elo","value":1300.358139132174,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_english_elo_votes","value":2572,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_english_elo_interval","value":11.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_english_elo","value":1297.3658165410413,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_english_elo_votes","value":25286,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_english_elo_interval","value":5.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_english_elo","value":1294.603087484243,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_english_elo_votes","value":14246,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_english_elo_interval","value":5.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_english_elo","value":1293.580174174125,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_english_elo_votes","value":29694,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_english_elo_interval","value":4.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_english_elo","value":1288.9418528053257,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_english_elo_votes","value":24863,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_english_elo_interval","value":5.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_english_elo","value":1282.5539292864894,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_english_elo_votes","value":20561,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_english_elo_interval","value":5.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_english_elo","value":1256.0860201564183,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_english_elo_votes","value":8740,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_english_elo_interval","value":7.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_english_elo","value":1247.8381266724969,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_english_elo_votes","value":2652,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_english_elo_interval","value":11.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_english_elo","value":1241.8492717999975,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_english_elo_votes","value":41283,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_english_elo_interval","value":4.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_english_elo","value":1237.5206134000564,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_english_elo_votes","value":5305,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_english_elo_interval","value":8.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_english_elo","value":1230.914654374906,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_english_elo_votes","value":14101,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_english_elo_interval","value":5.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_english_elo","value":1217.458771207032,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_english_elo_votes","value":26610,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_english_elo_interval","value":5.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_english_elo","value":1197.695354429878,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_english_elo_votes","value":5416,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_english_elo_interval","value":8.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_english_elo","value":1179.552592588842,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_english_elo_votes","value":4157,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_english_elo_interval","value":9.6,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_english_elo","value":1116.5799542039329,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_english_elo_votes","value":4320,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_english_elo_interval","value":9.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_non_english_elo","value":1521.6995914579047,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_non_english_elo_votes","value":3002,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_non_english_elo_interval","value":11.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_non_english_elo","value":1507.4921095442312,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_non_english_elo_votes","value":8652,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_non_english_elo_interval","value":7.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_non_english_elo","value":1506.90828454686,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_non_english_elo_votes","value":5130,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_non_english_elo_interval","value":8.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_non_english_elo","value":1500.46341712674,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_non_english_elo_votes","value":19383,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_non_english_elo","value":1491.0558099978905,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_non_english_elo_votes","value":22675,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_non_english_elo","value":1489.0083506462342,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_non_english_elo_votes","value":1917,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_non_english_elo_interval","value":13.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_non_english_elo","value":1488.0567415936907,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_non_english_elo_votes","value":45580,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_non_english_elo","value":1484.8695683058024,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_non_english_elo_votes","value":16312,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_non_english_elo","value":1480.9749193536106,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_non_english_elo_votes","value":10597,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_non_english_elo_interval","value":6.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_non_english_elo","value":1480.7119718970757,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_non_english_elo_votes","value":24075,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_non_english_elo","value":1480.4604145168944,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_non_english_elo_votes","value":34937,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_non_english_elo","value":1477.863899545365,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_non_english_elo_votes","value":4934,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_non_english_elo_interval","value":9.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_non_english_elo","value":1476.3855083388416,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_non_english_elo_votes","value":71523,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_non_english_elo_interval","value":3.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_non_english_elo","value":1475.447476644196,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_non_english_elo_votes","value":27913,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_non_english_elo","value":1473.3704652926845,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_non_english_elo_votes","value":2568,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_non_english_elo_interval","value":11.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_non_english_elo","value":1471.6970062095968,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_non_english_elo_votes","value":17180,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_non_english_elo","value":1471.075552410547,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_non_english_elo_votes","value":25424,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_non_english_elo","value":1469.5289288728072,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_non_english_elo_votes","value":20948,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_non_english_elo","value":1466.8943972373372,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_non_english_elo_votes","value":37842,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_non_english_elo","value":1464.9484205542253,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_non_english_elo_votes","value":35444,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_non_english_elo","value":1464.2966547874335,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_non_english_elo_votes","value":20322,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_non_english_elo","value":1460.656610593979,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_non_english_elo_votes","value":20756,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_non_english_elo","value":1454.1549919849735,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_non_english_elo_votes","value":4250,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_non_english_elo_interval","value":9.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_non_english_elo","value":1451.4994974884712,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_non_english_elo_votes","value":71251,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_non_english_elo_interval","value":3.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_non_english_elo","value":1450.8270694688658,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_non_english_elo_votes","value":24121,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_non_english_elo","value":1450.0249762672142,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_non_english_elo_votes","value":36060,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_non_english_elo","value":1449.3538354711627,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_non_english_elo_votes","value":44001,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_non_english_elo","value":1448.4105936831563,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_non_english_elo_votes","value":35940,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_non_english_elo","value":1446.3523272951015,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_non_english_elo_votes","value":21852,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_non_english_elo","value":1444.9012006809162,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_non_english_elo_votes","value":24357,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_non_english_elo","value":1440.0790378729182,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_non_english_elo_votes","value":38962,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_non_english_elo","value":1439.8978428373512,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_non_english_elo_votes","value":25702,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_non_english_elo_interval","value":5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_non_english_elo","value":1439.8161024842557,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_non_english_elo_votes","value":23697,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_non_english_elo","value":1438.78138994694,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_non_english_elo_votes","value":32302,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_non_english_elo","value":1437.5236378529148,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_non_english_elo_votes","value":41682,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_non_english_elo_interval","value":3.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_non_english_elo","value":1433.0042725492922,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_non_english_elo_votes","value":23960,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_non_english_elo","value":1432.8413210005488,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_non_english_elo_votes","value":6880,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_non_english_elo_interval","value":7.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_non_english_elo","value":1431.3296429325706,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_non_english_elo_votes","value":24940,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_non_english_elo","value":1431.1972157144228,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_non_english_elo_votes","value":28747,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_non_english_elo","value":1430.6500260179378,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_non_english_elo_votes","value":3815,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_non_english_elo_interval","value":9.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_non_english_elo","value":1430.1630651736598,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_non_english_elo_votes","value":16350,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_non_english_elo","value":1429.6977601524452,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_non_english_elo_votes","value":52251,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_non_english_elo_interval","value":3.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_non_english_elo","value":1429.5584866603044,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_non_english_elo_votes","value":4595,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_non_english_elo_interval","value":9.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_non_english_elo","value":1429.4006998861778,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_non_english_elo_votes","value":14467,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_non_english_elo_interval","value":6,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_non_english_elo","value":1426.4658499036136,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_non_english_elo_votes","value":21221,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_non_english_elo","value":1426.2939765067083,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_non_english_elo_votes","value":7548,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_non_english_elo_interval","value":7.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_non_english_elo","value":1426.1486731136326,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_non_english_elo_votes","value":20465,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_non_english_elo","value":1424.9220232774612,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_non_english_elo_votes","value":46922,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_non_english_elo_interval","value":3.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_non_english_elo","value":1423.9862353447897,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_non_english_elo_votes","value":26548,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_non_english_elo","value":1421.432518803864,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_non_english_elo_votes","value":3845,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_non_english_elo_interval","value":9.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_non_english_elo","value":1420.4394807060219,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_non_english_elo_votes","value":6027,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_non_english_elo_interval","value":7.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_non_english_elo","value":1420.171862416003,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_non_english_elo_votes","value":37548,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_non_english_elo","value":1420.1635041804213,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_non_english_elo_votes","value":4479,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_non_english_elo_interval","value":9.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_non_english_elo","value":1419.1503648780931,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_non_english_elo_votes","value":28857,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_non_english_elo","value":1418.8906066804107,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_non_english_elo_votes","value":17226,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_non_english_elo","value":1417.04405970512,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_non_english_elo_votes","value":7226,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_non_english_elo_interval","value":7.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_non_english_elo","value":1416.9916723843867,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_non_english_elo_votes","value":13664,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_non_english_elo","value":1416.6983625934226,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_non_english_elo_votes","value":24449,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_non_english_elo","value":1411.828011957262,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_non_english_elo_votes","value":9998,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_non_english_elo_interval","value":6.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_non_english_elo","value":1410.5452994846787,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_non_english_elo_votes","value":34711,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_non_english_elo","value":1409.36375556232,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_non_english_elo_votes","value":57028,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_non_english_elo_interval","value":3.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_non_english_elo","value":1409.2785074237775,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_non_english_elo_votes","value":70758,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_non_english_elo_interval","value":2.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_non_english_elo","value":1408.853793439274,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_non_english_elo_votes","value":28490,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_non_english_elo","value":1407.4242553358195,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_non_english_elo_votes","value":2028,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_non_english_elo_interval","value":12.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_non_english_elo","value":1406.8454779680203,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_non_english_elo_votes","value":12991,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_non_english_elo","value":1405.560197160691,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_non_english_elo_votes","value":45037,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_non_english_elo_interval","value":3.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_non_english_elo","value":1405.1741299428425,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_non_english_elo_votes","value":46249,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_non_english_elo_interval","value":3.89,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_non_english_elo","value":1404.8636699548797,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_non_english_elo_votes","value":34289,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_non_english_elo","value":1404.8140790688026,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_non_english_elo_votes","value":6388,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_non_english_elo_interval","value":8.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_non_english_elo","value":1404.6638695663069,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_non_english_elo_votes","value":6127,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_non_english_elo_interval","value":8.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_non_english_elo","value":1404.5098939521456,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_non_english_elo_votes","value":25991,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_non_english_elo","value":1404.2650074976143,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_non_english_elo_votes","value":6923,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_non_english_elo_interval","value":7.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_non_english_elo","value":1401.2177292464883,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_non_english_elo_votes","value":31572,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_non_english_elo","value":1400.3185111074324,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_non_english_elo_votes","value":16574,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_non_english_elo","value":1399.590870304287,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_non_english_elo_votes","value":19075,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_non_english_elo","value":1397.26047418955,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_non_english_elo_votes","value":4914,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_non_english_elo_interval","value":8.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_non_english_elo","value":1396.9300125923103,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_non_english_elo_votes","value":18083,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_non_english_elo","value":1389.621787276558,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_non_english_elo_votes","value":15918,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_non_english_elo","value":1386.1950703721102,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_non_english_elo_votes","value":6985,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_non_english_elo_interval","value":7.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_non_english_elo","value":1385.4331480041533,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_non_english_elo_votes","value":38561,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_non_english_elo","value":1385.0222456287786,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_non_english_elo_votes","value":35073,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_non_english_elo","value":1384.8491251468008,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_non_english_elo_votes","value":35171,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_non_english_elo","value":1382.3415646291996,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_non_english_elo_votes","value":49817,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_non_english_elo_interval","value":3.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_non_english_elo","value":1378.4154399631207,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_non_english_elo_votes","value":16889,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_non_english_elo","value":1376.6836469116852,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_non_english_elo_votes","value":84413,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_non_english_elo_interval","value":2.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_non_english_elo","value":1371.6769585919133,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_non_english_elo_votes","value":13555,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_non_english_elo","value":1369.6943951697358,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_non_english_elo_votes","value":26908,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.6,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_non_english_elo","value":1366.0434920004677,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_non_english_elo_votes","value":17400,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_non_english_elo","value":1362.69082747335,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_non_english_elo_votes","value":15291,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_non_english_elo","value":1361.212041954001,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_non_english_elo_votes","value":12751,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_non_english_elo_interval","value":6.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_non_english_elo","value":1359.3152138866546,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_non_english_elo_votes","value":33490,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_non_english_elo","value":1358.6955790523018,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_non_english_elo_votes","value":1668,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_non_english_elo_interval","value":14.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_non_english_elo","value":1358.4605958600623,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_non_english_elo_votes","value":11491,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_non_english_elo_interval","value":6.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_non_english_elo","value":1357.8558353696114,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_non_english_elo_votes","value":23546,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_non_english_elo","value":1355.4153835536272,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_non_english_elo_votes","value":4718,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_non_english_elo_interval","value":8.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_non_english_elo","value":1350.5954266377305,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_non_english_elo_votes","value":17137,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_non_english_elo","value":1345.6101540131958,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_non_english_elo_votes","value":14203,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_non_english_elo_interval","value":6.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_non_english_elo","value":1342.4769288667796,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_non_english_elo_votes","value":7571,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_non_english_elo_interval","value":7.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_non_english_elo","value":1337.7470994668276,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_non_english_elo_votes","value":24035,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_non_english_elo","value":1337.0640982300351,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_non_english_elo_votes","value":7235,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_non_english_elo_interval","value":7.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_non_english_elo","value":1336.5778518845502,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_non_english_elo_votes","value":24010,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_non_english_elo","value":1334.4036626669601,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_non_english_elo_votes","value":23612,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_non_english_elo","value":1330.546462640966,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_non_english_elo_votes","value":1989,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_non_english_elo_interval","value":13.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_non_english_elo","value":1330.198349667824,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_non_english_elo_votes","value":7369,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_non_english_elo_interval","value":7.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_non_english_elo","value":1325.0402309377685,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_non_english_elo_votes","value":15972,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_non_english_elo","value":1319.3823472517565,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_non_english_elo_votes","value":19349,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_non_english_elo","value":1318.6885668449652,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_non_english_elo_votes","value":7459,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_non_english_elo_interval","value":7.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_non_english_elo","value":1317.9252433726306,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_non_english_elo_votes","value":1499,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_non_english_elo_interval","value":14.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_non_english_elo","value":1317.8517103510562,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_non_english_elo_votes","value":20643,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_non_english_elo","value":1316.7017584998168,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_non_english_elo_votes","value":1696,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_non_english_elo_interval","value":13.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_non_english_elo","value":1313.0916471500082,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_non_english_elo_votes","value":3822,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_non_english_elo_interval","value":9.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_non_english_elo","value":1313.0694772961992,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_non_english_elo_votes","value":29460,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_non_english_elo","value":1312.7991034329996,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_non_english_elo_votes","value":4550,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_non_english_elo_interval","value":8.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_non_english_elo","value":1303.1476350778507,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_non_english_elo_votes","value":2794,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_non_english_elo_interval","value":11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_non_english_elo","value":1300.8055392953825,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_non_english_elo_votes","value":1842,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_non_english_elo_interval","value":14.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_non_english_elo","value":1299.7026420391592,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_non_english_elo_votes","value":28084,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_non_english_elo","value":1295.2546775743579,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_non_english_elo_votes","value":13832,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_non_english_elo","value":1282.7630576350202,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_non_english_elo_votes","value":52655,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_non_english_elo","value":1273.1929924228398,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_non_english_elo_votes","value":1599,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_non_english_elo_interval","value":13.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_non_english_elo","value":1269.0832165344757,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_non_english_elo_votes","value":20523,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_non_english_elo","value":1268.5227133355454,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_non_english_elo_votes","value":5894,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_non_english_elo_interval","value":8.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_non_english_elo","value":1266.202042575094,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_non_english_elo_votes","value":30970,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_non_english_elo","value":1261.637103842643,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_non_english_elo_votes","value":20213,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_non_english_elo","value":1259.9890760944484,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_non_english_elo_votes","value":2575,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_non_english_elo_interval","value":11.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_non_english_elo","value":1254.619476003894,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_non_english_elo_votes","value":18470,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_non_english_elo","value":1252.2882921670805,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_non_english_elo_votes","value":16775,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_non_english_elo","value":1251.8102091470423,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_non_english_elo_votes","value":18845,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_non_english_elo","value":1236.487537020878,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_non_english_elo_votes","value":20596,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_non_english_elo","value":1236.259964040984,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_non_english_elo_votes","value":25242,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_non_english_elo","value":1219.2256056200797,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_non_english_elo_votes","value":25546,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_non_english_elo","value":1216.9578813265298,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_non_english_elo_votes","value":34471,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_non_english_elo_interval","value":4.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_non_english_elo","value":1216.3847948994974,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_non_english_elo_votes","value":4561,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_non_english_elo_interval","value":8.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_non_english_elo","value":1204.5906481626218,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_non_english_elo_votes","value":2780,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_non_english_elo_interval","value":10.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_non_english_elo","value":1198.1356763434937,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_non_english_elo_votes","value":5941,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_non_english_elo_interval","value":7.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_non_english_elo","value":1196.7089136625734,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_non_english_elo_votes","value":10025,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_non_english_elo_interval","value":6.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_non_english_elo","value":1174.2583621484646,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_non_english_elo_votes","value":4724,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_non_english_elo_interval","value":8.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_non_english_elo","value":1148.0223433881424,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_non_english_elo_votes","value":22995,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_non_english_elo_interval","value":5.27,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_non_english_elo","value":1018.7902358746294,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_non_english_elo_votes","value":3779,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_non_english_elo_interval","value":11.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_non_english_elo","value":973.2842891895982,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_non_english_elo_votes","value":3725,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_non_english_elo_interval","value":11.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_chinese_elo","value":1608.3065495299288,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_chinese_elo_votes","value":363,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_chinese_elo_interval","value":31.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_chinese_elo","value":1585.6400689527263,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_chinese_elo_votes","value":1111,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_chinese_elo_interval","value":18.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_chinese_elo","value":1583.5693161916856,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_chinese_elo_votes","value":767,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_chinese_elo_interval","value":22.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_chinese_elo","value":1573.386191568005,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_chinese_elo_votes","value":2580,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_chinese_elo_interval","value":12.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_chinese_elo","value":1550.956846423685,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_chinese_elo_votes","value":2124,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_chinese_elo_interval","value":13.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_chinese_elo","value":1550.8165895655216,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_chinese_elo_votes","value":3070,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_chinese_elo_interval","value":11.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_chinese_elo","value":1550.1945873426644,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_chinese_elo_votes","value":5649,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_chinese_elo_interval","value":8.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_chinese_elo","value":1542.3252667184538,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_chinese_elo_votes","value":3131,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_chinese_elo_interval","value":11.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_chinese_elo","value":1539.901510124373,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_chinese_elo_votes","value":248,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_chinese_elo_interval","value":35.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_chinese_elo","value":1536.900935807565,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_chinese_elo_votes","value":553,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_chinese_elo_interval","value":25.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_chinese_elo","value":1535.9800183602852,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_chinese_elo_votes","value":2058,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_chinese_elo_interval","value":13.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_chinese_elo","value":1533.224276723136,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_chinese_elo_votes","value":4460,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_chinese_elo_interval","value":9.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_chinese_elo","value":1531.809074972938,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_chinese_elo_votes","value":4182,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_chinese_elo_interval","value":9.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_chinese_elo","value":1530.3512343412276,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_chinese_elo_votes","value":2691,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_chinese_elo_interval","value":11.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_chinese_elo","value":1528.2511664581207,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_chinese_elo_votes","value":1372,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_chinese_elo_interval","value":16.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_chinese_elo","value":1528.23309123456,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_chinese_elo_votes","value":2372,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_chinese_elo_interval","value":12.6,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_chinese_elo","value":1528.1542060222223,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_chinese_elo_votes","value":299,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_chinese_elo_interval","value":32.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_chinese_elo","value":1528.031707102576,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_chinese_elo_votes","value":2515,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_chinese_elo_interval","value":12.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_chinese_elo","value":1527.61336812433,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_chinese_elo_votes","value":8789,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_chinese_elo_interval","value":7.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_chinese_elo","value":1526.6337453685892,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_chinese_elo_votes","value":3113,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_chinese_elo_interval","value":11.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_chinese_elo","value":1526.402840694051,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_chinese_elo_votes","value":3441,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_chinese_elo_interval","value":10.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_chinese_elo","value":1520.6614958852551,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_chinese_elo_votes","value":2322,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_chinese_elo_interval","value":12.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_chinese_elo","value":1518.4974638578265,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_chinese_elo_votes","value":4141,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_chinese_elo_interval","value":9.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_chinese_elo","value":1515.6058572947181,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_chinese_elo_votes","value":3373,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_chinese_elo_interval","value":10.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_chinese_elo","value":1514.5652696469892,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_chinese_elo_votes","value":3415,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_chinese_elo_interval","value":10.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_chinese_elo","value":1514.328958336173,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_chinese_elo_votes","value":4393,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_chinese_elo_interval","value":9.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_chinese_elo","value":1513.2990268276535,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_chinese_elo_votes","value":871,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_chinese_elo_interval","value":20.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_chinese_elo","value":1510.5438123396261,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_chinese_elo_votes","value":2019,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_chinese_elo_interval","value":13.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_chinese_elo","value":1509.933351270101,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_chinese_elo_votes","value":2662,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_chinese_elo_interval","value":11.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_chinese_elo","value":1508.5703175513254,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_chinese_elo_votes","value":717,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_chinese_elo_interval","value":22.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_chinese_elo","value":1508.092735437761,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_chinese_elo_votes","value":573,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_chinese_elo_interval","value":24.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_chinese_elo","value":1507.4181172773933,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_chinese_elo_votes","value":9318,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_chinese_elo_interval","value":6.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_chinese_elo","value":1507.0187879532218,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_chinese_elo_votes","value":4858,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_chinese_elo_interval","value":9.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_chinese_elo","value":1506.752025453883,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_chinese_elo_votes","value":4397,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_chinese_elo_interval","value":9.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_chinese_elo","value":1502.279001429591,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_chinese_elo_votes","value":1743,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_chinese_elo_interval","value":14.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_chinese_elo","value":1499.1648118896746,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_chinese_elo_votes","value":2722,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_chinese_elo_interval","value":11.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_chinese_elo","value":1498.914880798152,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_chinese_elo_votes","value":6487,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_chinese_elo_interval","value":7.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_chinese_elo","value":1495.4147423160834,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_chinese_elo_votes","value":524,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_chinese_elo_interval","value":24.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_chinese_elo","value":1495.300257875042,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_chinese_elo_votes","value":1021,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_chinese_elo_interval","value":18.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_chinese_elo","value":1495.1101150050858,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_chinese_elo_votes","value":3427,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_chinese_elo_interval","value":10.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_chinese_elo","value":1494.6409102670145,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_chinese_elo_votes","value":3066,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_chinese_elo_interval","value":11.27,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_chinese_elo","value":1491.9999353327285,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_chinese_elo_votes","value":658,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_chinese_elo_interval","value":22.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_chinese_elo","value":1491.6011265381098,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_chinese_elo_votes","value":3197,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_chinese_elo_interval","value":10.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_chinese_elo","value":1491.5847776487103,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_chinese_elo_votes","value":4520,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_chinese_elo_interval","value":9.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_chinese_elo","value":1491.0348764187474,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_chinese_elo_votes","value":769,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_chinese_elo_interval","value":21.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_chinese_elo","value":1487.4793095711093,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_chinese_elo_votes","value":928,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_chinese_elo_interval","value":19.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_chinese_elo","value":1480.9137901556314,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_chinese_elo_votes","value":536,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_chinese_elo_interval","value":25.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_chinese_elo","value":1480.819950937631,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_chinese_elo_votes","value":3389,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_chinese_elo_interval","value":10.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_chinese_elo","value":1477.9902373956816,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_chinese_elo_votes","value":2058,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_chinese_elo_interval","value":13.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_chinese_elo","value":1477.6483221362546,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_chinese_elo_votes","value":3823,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_chinese_elo_interval","value":10.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_chinese_elo","value":1476.202542829487,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_chinese_elo_votes","value":2662,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_chinese_elo_interval","value":11.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_chinese_elo","value":1475.3262325405794,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_chinese_elo_votes","value":522,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_chinese_elo_interval","value":24.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_chinese_elo","value":1475.056640600034,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_chinese_elo_votes","value":2314,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_chinese_elo_interval","value":12.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_chinese_elo","value":1469.7900773104661,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_chinese_elo_votes","value":5403,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_chinese_elo_interval","value":8.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_chinese_elo","value":1469.376519586007,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_chinese_elo_votes","value":3218,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_chinese_elo_interval","value":11.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_chinese_elo","value":1467.9592892558912,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_chinese_elo_votes","value":2597,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_chinese_elo_interval","value":11.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_chinese_elo","value":1467.4088280708925,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_chinese_elo_votes","value":4069,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_chinese_elo_interval","value":9.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_chinese_elo","value":1467.3293115730703,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_chinese_elo_votes","value":2750,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_chinese_elo_interval","value":11.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_chinese_elo","value":1464.8258520585605,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_chinese_elo_votes","value":1783,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_chinese_elo_interval","value":14.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_chinese_elo","value":1464.6328213166084,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_chinese_elo_votes","value":7309,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_chinese_elo_interval","value":7.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_chinese_elo","value":1463.1414758534006,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_chinese_elo_votes","value":2589,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_chinese_elo_interval","value":12.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_chinese_elo","value":1462.7836126830625,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_chinese_elo_votes","value":3009,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_chinese_elo_interval","value":11.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_chinese_elo","value":1462.6044520579803,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_chinese_elo_votes","value":714,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_chinese_elo_interval","value":23.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_chinese_elo","value":1461.7195994219842,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_chinese_elo_votes","value":2122,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_chinese_elo_interval","value":12.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_chinese_elo","value":1461.3370054384195,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_chinese_elo_votes","value":1030,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_chinese_elo_interval","value":17.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_chinese_elo","value":1460.0939940669787,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_chinese_elo_votes","value":1729,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_chinese_elo_interval","value":14.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_chinese_elo","value":1459.9214615315032,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_chinese_elo_votes","value":4188,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_chinese_elo_interval","value":9.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_chinese_elo","value":1459.5895412550126,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_chinese_elo_votes","value":5887,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_chinese_elo_interval","value":8.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_chinese_elo","value":1456.6031836364564,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_chinese_elo_votes","value":2090,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_chinese_elo_interval","value":12.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_chinese_elo","value":1455.0684217090702,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_chinese_elo_votes","value":3729,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_chinese_elo_interval","value":10.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_chinese_elo","value":1452.698052201716,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_chinese_elo_votes","value":927,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_chinese_elo_interval","value":19.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_chinese_elo","value":1449.666834152159,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_chinese_elo_votes","value":9167,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_chinese_elo_interval","value":6.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_chinese_elo","value":1446.6421031150699,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_chinese_elo_votes","value":3575,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_chinese_elo_interval","value":10.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_chinese_elo","value":1445.8625030400794,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_chinese_elo_votes","value":3668,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_chinese_elo_interval","value":10.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_chinese_elo","value":1445.6012233904135,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_chinese_elo_votes","value":3931,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_chinese_elo_interval","value":10.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_chinese_elo","value":1445.5993527217142,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_chinese_elo_votes","value":3673,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_chinese_elo_interval","value":10.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_chinese_elo","value":1444.02014756499,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_chinese_elo_votes","value":620,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_chinese_elo_interval","value":23.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_chinese_elo","value":1441.9063658038335,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_chinese_elo_votes","value":1188,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_chinese_elo_interval","value":17.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_chinese_elo","value":1441.2419503274082,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_chinese_elo_votes","value":5534,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_chinese_elo_interval","value":8.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_chinese_elo","value":1437.051840203373,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_chinese_elo_votes","value":3891,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_chinese_elo_interval","value":9.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_chinese_elo","value":1432.6621696109432,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_chinese_elo_votes","value":1755,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_chinese_elo_interval","value":14.36,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_chinese_elo","value":1431.5113265118393,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_chinese_elo_votes","value":585,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_chinese_elo_interval","value":22.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_chinese_elo","value":1427.0384315794017,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_chinese_elo_votes","value":5945,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_chinese_elo_interval","value":8.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_chinese_elo","value":1425.9601278063792,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_chinese_elo_votes","value":2235,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_chinese_elo_interval","value":12.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_chinese_elo","value":1424.7539889921577,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_chinese_elo_votes","value":275,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_chinese_elo_interval","value":34.08,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_chinese_elo","value":1422.0460644818063,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_chinese_elo_votes","value":2342,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_chinese_elo_interval","value":12.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_chinese_elo","value":1421.4592478157656,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_chinese_elo_votes","value":4520,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_chinese_elo_interval","value":9.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_chinese_elo","value":1418.7429762107845,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_chinese_elo_votes","value":1662,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_chinese_elo_interval","value":14.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_chinese_elo","value":1418.131624025295,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_chinese_elo_votes","value":10532,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_chinese_elo_interval","value":6.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_chinese_elo","value":1416.971392178879,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_chinese_elo_votes","value":233,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_chinese_elo_interval","value":37.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_chinese_elo","value":1406.8207604609088,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_chinese_elo_votes","value":1060,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_chinese_elo_interval","value":17.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_chinese_elo","value":1402.6089097005588,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_chinese_elo_votes","value":823,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_chinese_elo_interval","value":20.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_chinese_elo","value":1393.8839598374955,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_chinese_elo_votes","value":1780,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_chinese_elo_interval","value":14.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_chinese_elo","value":1392.836560591589,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_chinese_elo_votes","value":2875,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_chinese_elo_interval","value":11.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_chinese_elo","value":1390.9273933657878,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_chinese_elo_votes","value":3844,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_chinese_elo_interval","value":10.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_chinese_elo","value":1390.306950645881,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_chinese_elo_votes","value":3034,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_chinese_elo_interval","value":10.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_chinese_elo","value":1385.9109442785602,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_chinese_elo_votes","value":1951,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_chinese_elo_interval","value":13.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_chinese_elo","value":1384.9036953818836,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_chinese_elo_votes","value":2276,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_chinese_elo_interval","value":12.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_chinese_elo","value":1381.936158898343,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_chinese_elo_votes","value":3312,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_chinese_elo_interval","value":10.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_chinese_elo","value":1378.510093106182,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_chinese_elo_votes","value":1181,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_chinese_elo_interval","value":17.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_chinese_elo","value":1372.3827679549513,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_chinese_elo_votes","value":2076,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_chinese_elo_interval","value":14.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_chinese_elo","value":1367.6056788619837,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_chinese_elo_votes","value":231,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_chinese_elo_interval","value":38.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_chinese_elo","value":1366.1153604152735,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_chinese_elo_votes","value":452,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_chinese_elo_interval","value":27.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_chinese_elo","value":1364.4275538947388,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_chinese_elo_votes","value":1080,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_chinese_elo_interval","value":17.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_chinese_elo","value":1360.1210032266404,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_chinese_elo_votes","value":2360,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_chinese_elo_interval","value":12.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_chinese_elo","value":1356.9469817586314,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_chinese_elo_votes","value":187,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_chinese_elo_interval","value":37.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_chinese_elo","value":1356.8103484339717,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_chinese_elo_votes","value":1791,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_chinese_elo_interval","value":14.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_chinese_elo","value":1356.00649914401,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_chinese_elo_votes","value":512,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_chinese_elo_interval","value":25.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_chinese_elo","value":1353.921068657354,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_chinese_elo_votes","value":3027,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_chinese_elo_interval","value":10.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_chinese_elo","value":1346.909479114092,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_chinese_elo_votes","value":1578,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_chinese_elo_interval","value":14.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_chinese_elo","value":1346.5109779902205,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_chinese_elo_votes","value":2849,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_chinese_elo_interval","value":11.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_chinese_elo","value":1337.0132202024738,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_chinese_elo_votes","value":235,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_chinese_elo_interval","value":36.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_chinese_elo","value":1328.6447911837117,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_chinese_elo_votes","value":2549,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_chinese_elo_interval","value":11.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_chinese_elo","value":1327.3707468424077,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_chinese_elo_votes","value":3823,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_chinese_elo_interval","value":9.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_chinese_elo","value":1319.479301664417,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_chinese_elo_votes","value":3880,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_chinese_elo_interval","value":9.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_chinese_elo","value":1314.8722244312796,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_chinese_elo_votes","value":664,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_chinese_elo_interval","value":22.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_chinese_elo","value":1277.2290750036136,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_chinese_elo_votes","value":11416,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_chinese_elo_interval","value":8.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_chinese_elo","value":1276.9316604062587,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_chinese_elo_votes","value":2599,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_chinese_elo_interval","value":12.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_chinese_elo","value":1272.380682550986,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_chinese_elo_votes","value":3329,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_chinese_elo_interval","value":11.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_chinese_elo","value":1270.0648542107358,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_chinese_elo_votes","value":246,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_chinese_elo_interval","value":35.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_chinese_elo","value":1264.48451010406,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_chinese_elo_votes","value":5778,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_chinese_elo_interval","value":9.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_chinese_elo","value":1254.4628938787234,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_chinese_elo_votes","value":2082,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_chinese_elo_interval","value":13.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_chinese_elo","value":1254.1186982590832,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_chinese_elo_votes","value":3778,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_chinese_elo_interval","value":10.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_chinese_elo","value":1252.59019752667,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_chinese_elo_votes","value":2228,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_chinese_elo_interval","value":13.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_chinese_elo","value":1240.34447707656,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_chinese_elo_votes","value":3933,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_chinese_elo_interval","value":10.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_chinese_elo","value":1226.388904227088,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_chinese_elo_votes","value":845,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_chinese_elo_interval","value":19.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_chinese_elo","value":1221.8921797537182,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_chinese_elo_votes","value":528,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_chinese_elo_interval","value":24.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_chinese_elo","value":1220.9392455168959,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_chinese_elo_votes","value":6872,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_chinese_elo_interval","value":8.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_chinese_elo","value":1217.0245627836698,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_chinese_elo_votes","value":3676,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_chinese_elo_interval","value":10.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_chinese_elo","value":1215.2433952767142,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_chinese_elo_votes","value":4846,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_chinese_elo_interval","value":9.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_chinese_elo","value":1211.4553478684852,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_chinese_elo_votes","value":1503,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_chinese_elo_interval","value":15.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_chinese_elo","value":1203.659932139457,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_chinese_elo_votes","value":1054,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_chinese_elo_interval","value":17.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_chinese_elo","value":1182.1970637668287,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_chinese_elo_votes","value":834,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_chinese_elo_interval","value":19.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_chinese_elo","value":1150.771300102153,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_chinese_elo_votes","value":4400,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_chinese_elo_interval","value":10.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_chinese_elo","value":1017.2526943065645,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_chinese_elo_votes","value":721,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_chinese_elo_interval","value":24.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_chinese_elo","value":958.6389749025556,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_chinese_elo_votes","value":674,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_chinese_elo_interval","value":26.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_german_elo","value":1525.860232179738,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_german_elo_votes","value":554,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_german_elo_interval","value":26.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_german_elo","value":1523.4121365833219,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_german_elo_votes","value":258,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_german_elo_interval","value":36.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_german_elo","value":1503.0960522091425,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_german_elo_votes","value":418,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_german_elo_interval","value":28.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_german_elo","value":1501.7533511316963,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_german_elo_votes","value":1292,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_german_elo_interval","value":17.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_german_elo","value":1501.7364449513434,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_german_elo_votes","value":280,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_german_elo_interval","value":35.36,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_german_elo","value":1497.5500382267553,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_german_elo_votes","value":603,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_german_elo_interval","value":24.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_german_elo","value":1495.2056972245869,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_german_elo_votes","value":1022,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_german_elo_interval","value":18.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_german_elo","value":1493.2875972489928,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_german_elo_votes","value":758,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_german_elo_interval","value":22.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_german_elo","value":1491.3185086872047,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_german_elo_votes","value":2125,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_german_elo_interval","value":14.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_german_elo","value":1489.4754676844598,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_german_elo_votes","value":651,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_german_elo_interval","value":23.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_german_elo","value":1487.1275042048337,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_german_elo_votes","value":2652,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_german_elo_interval","value":12.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_german_elo","value":1486.7472844339902,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_german_elo_votes","value":650,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_german_elo_interval","value":23.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_german_elo","value":1483.1665811431462,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_german_elo_votes","value":433,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_german_elo_interval","value":27.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_german_elo","value":1480.9529106532407,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_german_elo_votes","value":594,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_german_elo_interval","value":24.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_german_elo","value":1480.3646364709407,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_german_elo_votes","value":1113,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_german_elo_interval","value":18.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_german_elo","value":1475.5026602047385,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_german_elo_votes","value":644,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_german_elo_interval","value":23.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_german_elo","value":1472.648136862238,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_german_elo_votes","value":1095,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_german_elo_interval","value":18.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_german_elo","value":1472.3672541156177,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_german_elo_votes","value":1077,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_german_elo_interval","value":18.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_german_elo","value":1470.7570468364247,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_german_elo_votes","value":763,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_german_elo_interval","value":21.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_german_elo","value":1468.0186772267632,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_german_elo_votes","value":783,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_german_elo_interval","value":22.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_german_elo","value":1466.5539612766538,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_german_elo_votes","value":1009,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_german_elo_interval","value":19.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_german_elo","value":1466.399382025416,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_german_elo_votes","value":568,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_german_elo_interval","value":25.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_german_elo","value":1464.2924523625966,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_german_elo_votes","value":192,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_german_elo_interval","value":41.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_german_elo","value":1458.9478530292602,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_german_elo_votes","value":1285,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_german_elo_interval","value":17.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_german_elo","value":1458.4436361277194,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_german_elo_votes","value":690,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_german_elo_interval","value":22.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_german_elo","value":1457.9978099474242,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_german_elo_votes","value":997,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_german_elo_interval","value":19.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_german_elo","value":1454.9575101877072,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_german_elo_votes","value":707,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_german_elo_interval","value":22.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_german_elo","value":1453.8528069455033,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_german_elo_votes","value":654,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_german_elo_interval","value":23.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_german_elo","value":1453.129827534871,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_german_elo_votes","value":174,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_german_elo_interval","value":43.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_german_elo","value":1451.6653213537347,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_german_elo_votes","value":795,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_german_elo_interval","value":21.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_german_elo","value":1450.7900123971258,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_german_elo_votes","value":745,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_german_elo_interval","value":21.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_german_elo","value":1449.4381012520562,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_german_elo_votes","value":1134,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_german_elo_interval","value":18.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_german_elo","value":1448.243492474509,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_german_elo_votes","value":686,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_german_elo_interval","value":22.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_german_elo","value":1446.8788100012964,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_german_elo_votes","value":681,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_german_elo_interval","value":22.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_german_elo","value":1446.6766065012737,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_german_elo_votes","value":223,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_german_elo_interval","value":36.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_german_elo","value":1446.5875145261962,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_german_elo_votes","value":627,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_german_elo_interval","value":23.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_german_elo","value":1445.6862533262245,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_german_elo_votes","value":1455,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_german_elo_interval","value":16.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_german_elo","value":1444.978282666192,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_german_elo_votes","value":508,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_german_elo_interval","value":25.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_german_elo","value":1443.9740325819093,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_german_elo_votes","value":834,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_german_elo_interval","value":20.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_german_elo","value":1441.9070495762858,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_german_elo_votes","value":799,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_german_elo_interval","value":21.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_german_elo","value":1439.6394181836804,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_german_elo_votes","value":227,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_german_elo_interval","value":36.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_german_elo","value":1438.1353671071872,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_german_elo_votes","value":718,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_german_elo_interval","value":21.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_german_elo","value":1436.2944091536792,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_german_elo_votes","value":368,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_german_elo_interval","value":30.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_german_elo","value":1432.1693312819796,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_german_elo_votes","value":1812,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_german_elo_interval","value":14.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_german_elo","value":1431.85554472728,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_german_elo_votes","value":507,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_german_elo_interval","value":27.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_german_elo","value":1429.52570847326,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_german_elo_votes","value":1047,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_german_elo_interval","value":18.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_german_elo","value":1428.1205121509813,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_german_elo_votes","value":1221,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_german_elo_interval","value":17.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_german_elo","value":1427.1650106264542,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_german_elo_votes","value":1104,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_german_elo_interval","value":18.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_german_elo","value":1425.95993472788,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_german_elo_votes","value":223,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_german_elo_interval","value":37.36,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_german_elo","value":1425.2444214085558,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_german_elo_votes","value":427,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_german_elo_interval","value":27.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_german_elo","value":1424.1661571326204,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_german_elo_votes","value":279,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_german_elo_interval","value":35.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_german_elo","value":1423.6207755081732,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_german_elo_votes","value":179,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_german_elo_interval","value":42.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_german_elo","value":1421.449145100877,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_german_elo_votes","value":795,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_german_elo_interval","value":21.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_german_elo","value":1421.0554833933495,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_german_elo_votes","value":1356,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_german_elo_interval","value":16.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_german_elo","value":1419.7450895884442,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_german_elo_votes","value":1508,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_german_elo_interval","value":16.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_german_elo","value":1418.6415396905,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_german_elo_votes","value":841,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_german_elo_interval","value":21.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_german_elo","value":1417.2657691883846,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_german_elo_votes","value":2686,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_german_elo_interval","value":11.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_german_elo","value":1416.348936597861,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_german_elo_votes","value":748,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_german_elo_interval","value":22.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_german_elo","value":1416.2868782038877,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_german_elo_votes","value":492,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_german_elo_interval","value":26.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_german_elo","value":1409.083889393511,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_german_elo_votes","value":934,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_german_elo_interval","value":20.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_german_elo","value":1408.0111262193418,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_german_elo_votes","value":211,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_german_elo_interval","value":39.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_german_elo","value":1407.9327984180368,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_german_elo_votes","value":901,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_german_elo_interval","value":20.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_german_elo","value":1406.728053031703,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_german_elo_votes","value":539,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_german_elo_interval","value":25.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_german_elo","value":1406.6509282519023,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_german_elo_votes","value":540,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_german_elo_interval","value":25.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_german_elo","value":1405.0878735020501,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_german_elo_votes","value":1076,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_german_elo_interval","value":18.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_german_elo","value":1404.8584585765423,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_german_elo_votes","value":1567,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_german_elo_interval","value":15.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_german_elo","value":1404.233501536778,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_german_elo_votes","value":597,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_german_elo_interval","value":24.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_german_elo","value":1399.1837822524944,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_german_elo_votes","value":1467,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_german_elo_interval","value":16.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_german_elo","value":1394.9138242083495,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_german_elo_votes","value":1043,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_german_elo_interval","value":19.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_german_elo","value":1392.5220941699786,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_german_elo_votes","value":451,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_german_elo_interval","value":27.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_german_elo","value":1390.7234601230537,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_german_elo_votes","value":1075,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_german_elo_interval","value":18.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_german_elo","value":1381.0510309006472,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_german_elo_votes","value":1284,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_german_elo_interval","value":16.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_german_elo","value":1378.7710690001118,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_german_elo_votes","value":523,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_german_elo_interval","value":25.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_german_elo","value":1377.0382329500587,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_german_elo_votes","value":743,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_german_elo_interval","value":21.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_german_elo","value":1373.900782224543,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_german_elo_votes","value":2468,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_german_elo_interval","value":13.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_german_elo","value":1373.7489985340378,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_german_elo_votes","value":1223,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_german_elo_interval","value":17.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_german_elo","value":1370.3367279920194,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_german_elo_votes","value":166,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_german_elo_interval","value":42.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_german_elo","value":1367.5046283595975,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_german_elo_votes","value":936,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_german_elo_interval","value":20.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_german_elo","value":1367.1999926453057,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_german_elo_votes","value":488,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_german_elo_interval","value":25.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_german_elo","value":1365.7023561065432,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_german_elo_votes","value":592,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_german_elo_interval","value":24.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_german_elo","value":1361.5870804920187,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_german_elo_votes","value":1206,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_german_elo_interval","value":17.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_german_elo","value":1361.5669649314755,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_german_elo_votes","value":643,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_german_elo_interval","value":23.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_german_elo","value":1357.4861839032167,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_german_elo_votes","value":133,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_german_elo_interval","value":52.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_german_elo","value":1357.1697392077253,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_german_elo_votes","value":295,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_german_elo_interval","value":33.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_german_elo","value":1356.0000298647217,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_german_elo_votes","value":410,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_german_elo_interval","value":28.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_german_elo","value":1355.751216758604,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_german_elo_votes","value":346,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_german_elo_interval","value":32.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_german_elo","value":1353.6676501066065,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_german_elo_votes","value":671,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_german_elo_interval","value":22.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_german_elo","value":1353.3139715003638,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_german_elo_votes","value":179,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_german_elo_interval","value":43.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_german_elo","value":1350.2723101639913,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_german_elo_votes","value":1053,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_german_elo_interval","value":18.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_german_elo","value":1349.768927261569,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_german_elo_votes","value":880,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_german_elo_interval","value":20.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_german_elo","value":1342.916911124366,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_german_elo_votes","value":283,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_german_elo_interval","value":35.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_german_elo","value":1341.6623991290762,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_german_elo_votes","value":1371,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_german_elo_interval","value":16.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_german_elo","value":1341.0836076529968,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_german_elo_votes","value":172,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_german_elo_interval","value":40.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_german_elo","value":1341.0584232519439,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_german_elo_votes","value":200,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_german_elo_interval","value":40.89,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_german_elo","value":1336.8493485555443,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_german_elo_votes","value":556,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_german_elo_interval","value":24.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_german_elo","value":1336.1324042385907,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_german_elo_votes","value":228,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_german_elo_interval","value":39.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_german_elo","value":1335.783717766675,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_german_elo_votes","value":1216,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_german_elo_interval","value":17.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_german_elo","value":1326.6162176945356,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_german_elo_votes","value":206,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_german_elo_interval","value":41.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_german_elo","value":1324.88805348576,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_german_elo_votes","value":591,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_german_elo_interval","value":25.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_german_elo","value":1307.0078560043776,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_german_elo_votes","value":767,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_german_elo_interval","value":21.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_german_elo","value":1303.0499091940521,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_german_elo_votes","value":377,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_german_elo_interval","value":29.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_german_elo","value":1299.054470560115,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_german_elo_votes","value":1345,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_german_elo_interval","value":16.36,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_german_elo","value":1291.156739231511,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_german_elo_votes","value":1028,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_german_elo_interval","value":19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_german_elo","value":1287.842669008946,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_german_elo_votes","value":222,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_german_elo_interval","value":36.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_german_elo","value":1282.4373424811408,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_german_elo_votes","value":3573,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_german_elo_interval","value":13.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_german_elo","value":1280.5884336733093,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_german_elo_votes","value":162,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_german_elo_interval","value":42.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_german_elo","value":1272.6453489826079,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_german_elo_votes","value":797,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_german_elo_interval","value":21.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_german_elo","value":1272.0110084916382,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_german_elo_votes","value":1641,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_german_elo_interval","value":15.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_german_elo","value":1266.1161270637676,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_german_elo_votes","value":873,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_german_elo_interval","value":21.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_german_elo","value":1257.2971084751273,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_german_elo_votes","value":1202,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_german_elo_interval","value":17.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_german_elo","value":1254.8742300484496,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_german_elo_votes","value":217,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_german_elo_interval","value":40.36,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_german_elo","value":1253.9603119009264,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_german_elo_votes","value":1230,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_german_elo_interval","value":17.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_german_elo","value":1250.7353261443918,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_german_elo_votes","value":1223,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_german_elo_interval","value":16.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_german_elo","value":1233.494149590262,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_german_elo_votes","value":926,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_german_elo_interval","value":19.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_german_elo","value":1222.3976840529149,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_german_elo_votes","value":523,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_german_elo_interval","value":25.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_german_elo","value":1221.6714337038968,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_german_elo_votes","value":1353,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_german_elo_interval","value":17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_german_elo","value":1215.910873661633,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_german_elo_votes","value":267,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_german_elo_interval","value":33.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_german_elo","value":1211.3496457840367,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_german_elo_votes","value":301,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_german_elo_interval","value":33.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_german_elo","value":1208.9250875860812,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_german_elo_votes","value":2037,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_german_elo_interval","value":14.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_german_elo","value":1176.1997085410096,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_german_elo_votes","value":275,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_german_elo_interval","value":32.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_german_elo","value":1144.2795412843277,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_german_elo_votes","value":1295,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_german_elo_interval","value":17.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_german_elo","value":1056.1232030466765,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_german_elo_votes","value":232,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_german_elo_interval","value":40.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_german_elo","value":1013.685329347998,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_german_elo_votes","value":247,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_german_elo_interval","value":39.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_japanese_elo","value":1560.0647487351,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_japanese_elo_votes","value":258,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_japanese_elo_interval","value":40.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_japanese_elo","value":1515.395485379089,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_japanese_elo_votes","value":554,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_japanese_elo_interval","value":27.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_japanese_elo","value":1511.659843241374,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_japanese_elo_votes","value":435,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_japanese_elo_interval","value":30.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_japanese_elo","value":1506.3588037147247,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_japanese_elo_votes","value":612,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_japanese_elo_interval","value":25.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_japanese_elo","value":1506.2966895677416,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_japanese_elo_votes","value":667,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_japanese_elo_interval","value":25.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_japanese_elo","value":1498.4957407209247,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_japanese_elo_votes","value":907,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_japanese_elo_interval","value":21.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_japanese_elo","value":1492.8273540839277,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_japanese_elo_votes","value":1526,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_japanese_elo_interval","value":17.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_japanese_elo","value":1489.3034757448515,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_japanese_elo_votes","value":614,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_japanese_elo_interval","value":26.08,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_japanese_elo","value":1488.010454361176,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_japanese_elo_votes","value":930,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_japanese_elo_interval","value":21.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_japanese_elo","value":1486.2340539914046,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_japanese_elo_votes","value":695,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_japanese_elo_interval","value":24.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_japanese_elo","value":1484.69332951613,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_japanese_elo_votes","value":676,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_japanese_elo_interval","value":24.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_japanese_elo","value":1480.954538018806,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_japanese_elo_votes","value":293,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_japanese_elo_interval","value":36.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_japanese_elo","value":1476.3147252233623,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_japanese_elo_votes","value":618,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_japanese_elo_interval","value":25.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_japanese_elo","value":1473.8546926685983,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_japanese_elo_votes","value":715,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_japanese_elo_interval","value":24.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_japanese_elo","value":1470.909175805296,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_japanese_elo_votes","value":623,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_japanese_elo_interval","value":26.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_japanese_elo","value":1469.496324552534,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_japanese_elo_votes","value":505,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_japanese_elo_interval","value":28.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_japanese_elo","value":1460.5760795381843,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_japanese_elo_votes","value":2061,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_japanese_elo_interval","value":14.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_japanese_elo","value":1456.0174289781373,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_japanese_elo_votes","value":676,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_japanese_elo_interval","value":25.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_japanese_elo","value":1453.2082146892112,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_japanese_elo_votes","value":459,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_japanese_elo_interval","value":27.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_japanese_elo","value":1447.8004016153384,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_japanese_elo_votes","value":737,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_japanese_elo_interval","value":23.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_japanese_elo","value":1445.5654820647405,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_japanese_elo_votes","value":722,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_japanese_elo_interval","value":23.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_japanese_elo","value":1443.1645977799697,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_japanese_elo_votes","value":501,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_japanese_elo_interval","value":27.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_japanese_elo","value":1441.0995726566975,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_japanese_elo_votes","value":892,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_japanese_elo_interval","value":21.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_japanese_elo","value":1438.7217950715935,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_japanese_elo_votes","value":125,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_japanese_elo_interval","value":54.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_japanese_elo","value":1435.54815351961,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_japanese_elo_votes","value":851,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_japanese_elo_interval","value":22.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_japanese_elo","value":1435.145445254067,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_japanese_elo_votes","value":616,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_japanese_elo_interval","value":25.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_japanese_elo","value":1430.6949749059486,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_japanese_elo_votes","value":530,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_japanese_elo_interval","value":27.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_japanese_elo","value":1428.693849742373,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_japanese_elo_votes","value":1136,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_japanese_elo_interval","value":19.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_japanese_elo","value":1427.1359973768085,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_japanese_elo_votes","value":583,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_japanese_elo_interval","value":26.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_japanese_elo","value":1426.0531482705949,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_japanese_elo_votes","value":638,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_japanese_elo_interval","value":25.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_japanese_elo","value":1424.7588962712007,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_japanese_elo_votes","value":737,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_japanese_elo_interval","value":23.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_japanese_elo","value":1420.0193468422583,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_japanese_elo_votes","value":801,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_japanese_elo_interval","value":22.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_japanese_elo","value":1419.6336560658328,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_japanese_elo_votes","value":446,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_japanese_elo_interval","value":29.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_japanese_elo","value":1416.3004397948343,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_japanese_elo_votes","value":276,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_japanese_elo_interval","value":36.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_japanese_elo","value":1415.4420210878293,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_japanese_elo_votes","value":775,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_japanese_elo_interval","value":22.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_japanese_elo","value":1414.0934295313516,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_japanese_elo_votes","value":644,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_japanese_elo_interval","value":25.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_japanese_elo","value":1412.9528485616295,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_japanese_elo_votes","value":647,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_japanese_elo_interval","value":24.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_japanese_elo","value":1412.146376907326,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_japanese_elo_votes","value":678,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_japanese_elo_interval","value":24.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_japanese_elo","value":1411.781484722396,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_japanese_elo_votes","value":640,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_japanese_elo_interval","value":24.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_japanese_elo","value":1409.563138437315,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_japanese_elo_votes","value":1071,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_japanese_elo_interval","value":20.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_japanese_elo","value":1408.7043348699335,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_japanese_elo_votes","value":524,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_japanese_elo_interval","value":27.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_japanese_elo","value":1403.6160540015537,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_japanese_elo_votes","value":1419,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_japanese_elo_interval","value":17.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_japanese_elo","value":1401.138289374192,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_japanese_elo_votes","value":528,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_japanese_elo_interval","value":27.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_japanese_elo","value":1399.018511149414,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_japanese_elo_votes","value":1439,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_japanese_elo_interval","value":16.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_japanese_elo","value":1396.409697710132,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_japanese_elo_votes","value":2044,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_japanese_elo_interval","value":13.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_japanese_elo","value":1396.3379797475436,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_japanese_elo_votes","value":221,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_japanese_elo_interval","value":40.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_japanese_elo","value":1395.2810476379082,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_japanese_elo_votes","value":318,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_japanese_elo_interval","value":33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_japanese_elo","value":1392.83962615845,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_japanese_elo_votes","value":373,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_japanese_elo_interval","value":29.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_japanese_elo","value":1392.2923517854604,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_japanese_elo_votes","value":414,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_japanese_elo_interval","value":30.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_japanese_elo","value":1390.9055633281469,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_japanese_elo_votes","value":620,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_japanese_elo_interval","value":24.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_japanese_elo","value":1389.7034670870407,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_japanese_elo_votes","value":785,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_japanese_elo_interval","value":21.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_japanese_elo","value":1389.556993934,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_japanese_elo_votes","value":554,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_japanese_elo_interval","value":26.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_japanese_elo","value":1388.9250337686453,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_japanese_elo_votes","value":653,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_japanese_elo_interval","value":24.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_japanese_elo","value":1386.3683479455037,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_japanese_elo_votes","value":442,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_japanese_elo_interval","value":29.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_japanese_elo","value":1384.801937874978,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_japanese_elo_votes","value":170,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_japanese_elo_interval","value":44.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_japanese_elo","value":1380.6147696838157,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_japanese_elo_votes","value":953,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_japanese_elo_interval","value":21.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_japanese_elo","value":1380.469707818926,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_japanese_elo_votes","value":497,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_japanese_elo_interval","value":28.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_japanese_elo","value":1378.7295001578273,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_japanese_elo_votes","value":854,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_japanese_elo_interval","value":22.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_japanese_elo","value":1375.056973691765,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_japanese_elo_votes","value":624,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_japanese_elo_interval","value":25.27,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_japanese_elo","value":1374.3601844953469,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_japanese_elo_votes","value":1198,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_japanese_elo_interval","value":17.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_japanese_elo","value":1368.4011055715494,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_japanese_elo_votes","value":665,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_japanese_elo_interval","value":23.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_japanese_elo","value":1366.9995436650422,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_japanese_elo_votes","value":257,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_japanese_elo_interval","value":36.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_japanese_elo","value":1358.139903998721,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_japanese_elo_votes","value":452,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_japanese_elo_interval","value":28.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_japanese_elo","value":1355.1420525342992,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_japanese_elo_votes","value":225,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_japanese_elo_interval","value":42.27,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_japanese_elo","value":1353.752489689095,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_japanese_elo_votes","value":204,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_japanese_elo_interval","value":45.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_japanese_elo","value":1352.9044863784136,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_japanese_elo_votes","value":679,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_japanese_elo_interval","value":24.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_japanese_elo","value":1347.9658745173178,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_japanese_elo_votes","value":845,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_japanese_elo_interval","value":20.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_japanese_elo","value":1345.9841639919248,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_japanese_elo_votes","value":581,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_japanese_elo_interval","value":26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_japanese_elo","value":1345.6503363915774,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_japanese_elo_votes","value":226,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_japanese_elo_interval","value":39.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_japanese_elo","value":1343.1163663653713,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_japanese_elo_votes","value":610,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_japanese_elo_interval","value":25.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_japanese_elo","value":1340.9054046256906,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_japanese_elo_votes","value":459,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_japanese_elo_interval","value":28.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_japanese_elo","value":1338.146945733267,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_japanese_elo_votes","value":1712,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_japanese_elo_interval","value":16.36,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_japanese_elo","value":1337.7068456016104,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_japanese_elo_votes","value":767,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_japanese_elo_interval","value":22.08,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_japanese_elo","value":1332.9259652615465,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_japanese_elo_votes","value":1056,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_japanese_elo_interval","value":18.89,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_japanese_elo","value":1331.2451696894523,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_japanese_elo_votes","value":148,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_japanese_elo_interval","value":49.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_japanese_elo","value":1330.346744055178,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_japanese_elo_votes","value":574,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_japanese_elo_interval","value":25.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_japanese_elo","value":1325.5476279342186,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_japanese_elo_votes","value":251,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_japanese_elo_interval","value":38.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_japanese_elo","value":1318.9999949574217,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_japanese_elo_votes","value":1136,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_japanese_elo_interval","value":18.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_japanese_elo","value":1315.3554754282559,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_japanese_elo_votes","value":365,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_japanese_elo_interval","value":33.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_japanese_elo","value":1311.2130495439792,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_japanese_elo_votes","value":283,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_japanese_elo_interval","value":36.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_japanese_elo","value":1310.392950309907,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_japanese_elo_votes","value":922,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_japanese_elo_interval","value":20.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_japanese_elo","value":1308.2735314566376,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_japanese_elo_votes","value":1075,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_japanese_elo_interval","value":19.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_japanese_elo","value":1305.7517055192423,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_japanese_elo_votes","value":540,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_japanese_elo_interval","value":27.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_japanese_elo","value":1289.6272139659777,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_japanese_elo_votes","value":1002,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_japanese_elo_interval","value":19.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_japanese_elo","value":1286.7171433797596,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_japanese_elo_votes","value":1052,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_japanese_elo_interval","value":18.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_japanese_elo","value":1285.5911897526535,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_japanese_elo_votes","value":374,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_japanese_elo_interval","value":30.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_japanese_elo","value":1285.2956351828238,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_japanese_elo_votes","value":1236,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_japanese_elo_interval","value":17.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_japanese_elo","value":1280.1957697967366,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_japanese_elo_votes","value":206,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_japanese_elo_interval","value":41.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_japanese_elo","value":1273.223032304982,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_japanese_elo_votes","value":115,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_japanese_elo_interval","value":58.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_japanese_elo","value":1264.7671296570084,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_japanese_elo_votes","value":1412,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_japanese_elo_interval","value":16.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_japanese_elo","value":1261.2979490838693,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_japanese_elo_votes","value":1111,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_japanese_elo_interval","value":21.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_japanese_elo","value":1256.6992729176723,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_japanese_elo_votes","value":2674,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_japanese_elo_interval","value":15.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_japanese_elo","value":1254.141339037933,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_japanese_elo_votes","value":733,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_japanese_elo_interval","value":22.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_japanese_elo","value":1244.314538225436,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_japanese_elo_votes","value":246,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_japanese_elo_interval","value":38.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_japanese_elo","value":1234.0955182364937,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_japanese_elo_votes","value":1104,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_japanese_elo_interval","value":18.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_japanese_elo","value":1226.4030047237452,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_japanese_elo_votes","value":147,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_japanese_elo_interval","value":49.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_japanese_elo","value":1216.9671463433276,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_japanese_elo_votes","value":845,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_japanese_elo_interval","value":22.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_japanese_elo","value":1215.5552521936188,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_japanese_elo_votes","value":1793,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_japanese_elo_interval","value":15.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_japanese_elo","value":1207.7258476823374,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_japanese_elo_votes","value":809,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_japanese_elo_interval","value":21.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_japanese_elo","value":1206.3536749858733,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_japanese_elo_votes","value":764,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_japanese_elo_interval","value":22.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_japanese_elo","value":1205.9416882184285,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_japanese_elo_votes","value":936,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_japanese_elo_interval","value":21.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_japanese_elo","value":1198.3316760502885,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_japanese_elo_votes","value":160,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_japanese_elo_interval","value":45.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_japanese_elo","value":1187.4457678336294,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_japanese_elo_votes","value":1249,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_japanese_elo_interval","value":17.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_japanese_elo","value":1179.7367151179988,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_japanese_elo_votes","value":788,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_japanese_elo_interval","value":21.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_japanese_elo","value":1175.3780139477112,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_japanese_elo_votes","value":1808,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_japanese_elo_interval","value":15.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_japanese_elo","value":1171.0690481597821,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_japanese_elo_votes","value":368,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_japanese_elo_interval","value":37.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_japanese_elo","value":1166.0911780134002,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_japanese_elo_votes","value":210,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_japanese_elo_interval","value":37.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_japanese_elo","value":1158.2605707563534,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_japanese_elo_votes","value":500,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_japanese_elo_interval","value":26.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_japanese_elo","value":1150.2196845980666,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_japanese_elo_votes","value":1171,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_japanese_elo_interval","value":18.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_japanese_elo","value":1143.1223404792072,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_japanese_elo_votes","value":254,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_japanese_elo_interval","value":33.36,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_japanese_elo","value":1132.3273559099162,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_japanese_elo_votes","value":1428,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_japanese_elo_interval","value":17.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_japanese_elo","value":1110.858370269991,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_japanese_elo_votes","value":269,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_japanese_elo_interval","value":36.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_japanese_elo","value":1060.899189701854,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_japanese_elo_votes","value":1234,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_japanese_elo_interval","value":19.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_korean_elo","value":1520.8297960482596,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_korean_elo_votes","value":237,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_korean_elo_interval","value":38.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_korean_elo","value":1520.737114465999,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_korean_elo_votes","value":637,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_korean_elo_interval","value":24.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_korean_elo","value":1497.4314048208867,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_korean_elo_votes","value":322,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_korean_elo_interval","value":33.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_korean_elo","value":1491.0179286992163,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_korean_elo_votes","value":792,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_korean_elo_interval","value":22.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_korean_elo","value":1480.5814336462329,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_korean_elo_votes","value":503,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_korean_elo_interval","value":27.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_korean_elo","value":1472.982175372813,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_korean_elo_votes","value":180,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_korean_elo_interval","value":41.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_korean_elo","value":1465.0101320447961,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_korean_elo_votes","value":1541,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_korean_elo_interval","value":16.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_korean_elo","value":1464.4653451937982,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_korean_elo_votes","value":1149,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_korean_elo_interval","value":18.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_korean_elo","value":1463.6527996472576,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_korean_elo_votes","value":585,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_korean_elo_interval","value":25.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_korean_elo","value":1461.5508417958126,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_korean_elo_votes","value":680,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_korean_elo_interval","value":24.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_korean_elo","value":1460.0491826600228,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_korean_elo_votes","value":700,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_korean_elo_interval","value":22.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_korean_elo","value":1459.2835729656758,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_korean_elo_votes","value":1189,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_korean_elo_interval","value":18.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_korean_elo","value":1458.1315491419691,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_korean_elo_votes","value":805,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_korean_elo_interval","value":21.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_korean_elo","value":1454.4398337169384,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_korean_elo_votes","value":2263,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_korean_elo_interval","value":14.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_korean_elo","value":1449.1915590520657,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_korean_elo_votes","value":872,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_korean_elo_interval","value":20.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_korean_elo","value":1447.5721961430027,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_korean_elo_votes","value":1112,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_korean_elo_interval","value":19.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_korean_elo","value":1442.116871240549,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_korean_elo_votes","value":787,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_korean_elo_interval","value":22.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_korean_elo","value":1438.9562691971992,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_korean_elo_votes","value":586,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_korean_elo_interval","value":25.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_korean_elo","value":1435.4685553322336,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_korean_elo_votes","value":1381,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_korean_elo_interval","value":17.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_korean_elo","value":1434.7180352154041,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_korean_elo_votes","value":2499,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_korean_elo_interval","value":12.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_korean_elo","value":1431.935890292199,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_korean_elo_votes","value":1107,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_korean_elo_interval","value":19.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_korean_elo","value":1430.032756030969,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_korean_elo_votes","value":708,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_korean_elo_interval","value":22.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_korean_elo","value":1427.2929938639306,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_korean_elo_votes","value":840,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_korean_elo_interval","value":21.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_korean_elo","value":1427.2278252486879,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_korean_elo_votes","value":734,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_korean_elo_interval","value":22.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_korean_elo","value":1423.5905947091117,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_korean_elo_votes","value":1170,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_korean_elo_interval","value":18.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_korean_elo","value":1422.3334172248694,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_korean_elo_votes","value":1192,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_korean_elo_interval","value":18.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_korean_elo","value":1421.9567551727728,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_korean_elo_votes","value":553,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_korean_elo_interval","value":24.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_korean_elo","value":1418.2018417299032,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_korean_elo_votes","value":224,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_korean_elo_interval","value":40.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_korean_elo","value":1415.9558179283645,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_korean_elo_votes","value":788,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_korean_elo_interval","value":21.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_korean_elo","value":1414.4063229320075,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_korean_elo_votes","value":836,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_korean_elo_interval","value":21.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_korean_elo","value":1413.018769670096,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_korean_elo_votes","value":873,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_korean_elo_interval","value":20.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_korean_elo","value":1410.77094173758,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_korean_elo_votes","value":1153,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_korean_elo_interval","value":18.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_korean_elo","value":1409.126578258768,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_korean_elo_votes","value":1111,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_korean_elo_interval","value":18.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_korean_elo","value":1407.3927514256607,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_korean_elo_votes","value":715,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_korean_elo_interval","value":23.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_korean_elo","value":1405.7518789759054,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_korean_elo_votes","value":731,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_korean_elo_interval","value":22.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_korean_elo","value":1403.175170060854,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_korean_elo_votes","value":755,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_korean_elo_interval","value":22.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_korean_elo","value":1401.7638920327422,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_korean_elo_votes","value":1329,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_korean_elo_interval","value":16.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_korean_elo","value":1400.4844891780099,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_korean_elo_votes","value":663,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_korean_elo_interval","value":23.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_korean_elo","value":1400.05268912991,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_korean_elo_votes","value":617,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_korean_elo_interval","value":24.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_korean_elo","value":1398.9657351803796,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_korean_elo_votes","value":177,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_korean_elo_interval","value":43.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_korean_elo","value":1397.3309345295654,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_korean_elo_votes","value":262,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_korean_elo_interval","value":36.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_korean_elo","value":1396.9554867326528,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_korean_elo_votes","value":220,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_korean_elo_interval","value":38.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_korean_elo","value":1396.081735960688,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_korean_elo_votes","value":396,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_korean_elo_interval","value":31.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_korean_elo","value":1395.7691349142667,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_korean_elo_votes","value":567,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_korean_elo_interval","value":25.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_korean_elo","value":1394.211483121433,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_korean_elo_votes","value":325,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_korean_elo_interval","value":33.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_korean_elo","value":1392.4479362812583,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_korean_elo_votes","value":1066,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_korean_elo_interval","value":19.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_korean_elo","value":1390.571201596486,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_korean_elo_votes","value":1821,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_korean_elo_interval","value":14.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_korean_elo","value":1387.066167272745,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_korean_elo_votes","value":394,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_korean_elo_interval","value":29.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_korean_elo","value":1385.4535175669446,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_korean_elo_votes","value":342,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_korean_elo_interval","value":31.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_korean_elo","value":1385.1254073135915,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_korean_elo_votes","value":2376,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_korean_elo_interval","value":13.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_korean_elo","value":1385.0709215524478,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_korean_elo_votes","value":190,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_korean_elo_interval","value":43.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_korean_elo","value":1384.386536078084,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_korean_elo_votes","value":189,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_korean_elo_interval","value":43.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_korean_elo","value":1382.6781446867483,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_korean_elo_votes","value":1570,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_korean_elo_interval","value":16.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_korean_elo","value":1382.2933242182621,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_korean_elo_votes","value":899,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_korean_elo_interval","value":20.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_korean_elo","value":1380.3976124742674,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_korean_elo_votes","value":656,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_korean_elo_interval","value":23.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_korean_elo","value":1378.8663284373192,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_korean_elo_votes","value":819,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_korean_elo_interval","value":21.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_korean_elo","value":1375.05264888818,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_korean_elo_votes","value":204,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_korean_elo_interval","value":40.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_korean_elo","value":1374.0950170268086,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_korean_elo_votes","value":1302,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_korean_elo_interval","value":17.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_korean_elo","value":1373.2809882087395,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_korean_elo_votes","value":1192,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_korean_elo_interval","value":18.6,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_korean_elo","value":1372.075929835411,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_korean_elo_votes","value":212,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_korean_elo_interval","value":39.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_korean_elo","value":1370.8763654813333,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_korean_elo_votes","value":989,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_korean_elo_interval","value":19.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_korean_elo","value":1370.2374459439616,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_korean_elo_votes","value":1200,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_korean_elo_interval","value":18.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_korean_elo","value":1369.7345072394282,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_korean_elo_votes","value":796,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_korean_elo_interval","value":21.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_korean_elo","value":1364.2867099993246,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_korean_elo_votes","value":583,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_korean_elo_interval","value":25.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_korean_elo","value":1364.0842642958544,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_korean_elo_votes","value":1613,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_korean_elo_interval","value":15.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_korean_elo","value":1363.3610356328481,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_korean_elo_votes","value":523,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_korean_elo_interval","value":26.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_korean_elo","value":1361.46606671306,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_korean_elo_votes","value":809,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_korean_elo_interval","value":21.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_korean_elo","value":1359.9440475145498,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_korean_elo_votes","value":323,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_korean_elo_interval","value":34.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_korean_elo","value":1359.904995790328,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_korean_elo_votes","value":820,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_korean_elo_interval","value":21.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_korean_elo","value":1358.9589011353848,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_korean_elo_votes","value":448,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_korean_elo_interval","value":28.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_korean_elo","value":1355.2217230774052,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_korean_elo_votes","value":1130,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_korean_elo_interval","value":19.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_korean_elo","value":1354.1710121396195,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_korean_elo_votes","value":484,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_korean_elo_interval","value":27.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_korean_elo","value":1353.1118448087504,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_korean_elo_votes","value":477,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_korean_elo_interval","value":27.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_korean_elo","value":1350.531209874154,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_korean_elo_votes","value":1089,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_korean_elo_interval","value":18.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_korean_elo","value":1346.1280331703472,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_korean_elo_votes","value":2378,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_korean_elo_interval","value":13.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_korean_elo","value":1343.7602911092627,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_korean_elo_votes","value":1075,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_korean_elo_interval","value":19.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_korean_elo","value":1338.6205235436266,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_korean_elo_votes","value":1059,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_korean_elo_interval","value":18.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_korean_elo","value":1330.6967411134046,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_korean_elo_votes","value":593,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_korean_elo_interval","value":24.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_korean_elo","value":1320.5146075181326,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_korean_elo_votes","value":1034,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_korean_elo_interval","value":19.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_korean_elo","value":1318.8829815174577,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_korean_elo_votes","value":969,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_korean_elo_interval","value":19.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_korean_elo","value":1313.6770136368277,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_korean_elo_votes","value":1535,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_korean_elo_interval","value":16.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_korean_elo","value":1313.5914627936963,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_korean_elo_votes","value":241,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_korean_elo_interval","value":40.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_korean_elo","value":1312.269204096603,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_korean_elo_votes","value":986,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_korean_elo_interval","value":19.6,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_korean_elo","value":1310.1772244532722,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_korean_elo_votes","value":356,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_korean_elo_interval","value":32.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_korean_elo","value":1307.6586749698881,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_korean_elo_votes","value":889,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_korean_elo_interval","value":20.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_korean_elo","value":1307.5049093189282,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_korean_elo_votes","value":674,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_korean_elo_interval","value":23.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_korean_elo","value":1307.0615244856576,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_korean_elo_votes","value":662,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_korean_elo_interval","value":24.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_korean_elo","value":1305.434070586914,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_korean_elo_votes","value":612,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_korean_elo_interval","value":25.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_korean_elo","value":1303.9990444693872,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_korean_elo_votes","value":534,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_korean_elo_interval","value":26.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_korean_elo","value":1298.152393741638,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_korean_elo_votes","value":807,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_korean_elo_interval","value":21.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_korean_elo","value":1285.1465403229322,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_korean_elo_votes","value":1116,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_korean_elo_interval","value":18.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_korean_elo","value":1283.1573361522574,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_korean_elo_votes","value":160,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_korean_elo_interval","value":48.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_korean_elo","value":1282.7814408138431,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_korean_elo_votes","value":239,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_korean_elo_interval","value":40.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_korean_elo","value":1282.7297975036154,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_korean_elo_votes","value":680,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_korean_elo_interval","value":23.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_korean_elo","value":1269.287358555392,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_korean_elo_votes","value":225,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_korean_elo_interval","value":40.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_korean_elo","value":1265.8857165926888,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_korean_elo_votes","value":672,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_korean_elo_interval","value":23.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_korean_elo","value":1262.0167441369658,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_korean_elo_votes","value":476,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_korean_elo_interval","value":26.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_korean_elo","value":1258.8527947789285,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_korean_elo_votes","value":1103,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_korean_elo_interval","value":18.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_korean_elo","value":1235.8357471668232,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_korean_elo_votes","value":228,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_korean_elo_interval","value":40.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_korean_elo","value":1233.85198979427,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_korean_elo_votes","value":3517,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_korean_elo_interval","value":17.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_korean_elo","value":1232.5789092086197,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_korean_elo_votes","value":730,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_korean_elo_interval","value":24.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_korean_elo","value":1218.2684060456374,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_korean_elo_votes","value":712,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_korean_elo_interval","value":24.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_korean_elo","value":1206.9278147941782,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_korean_elo_votes","value":650,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_korean_elo_interval","value":25.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_korean_elo","value":1206.891869012409,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_korean_elo_votes","value":714,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_korean_elo_interval","value":23.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_korean_elo","value":1203.682463659118,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_korean_elo_votes","value":799,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_korean_elo_interval","value":21.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_korean_elo","value":1195.2309640310245,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_korean_elo_votes","value":1087,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_korean_elo_interval","value":20.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_korean_elo","value":1188.163290806592,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_korean_elo_votes","value":231,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_korean_elo_interval","value":39.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_korean_elo","value":1188.0378521828502,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_korean_elo_votes","value":527,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_korean_elo_interval","value":27.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_korean_elo","value":1173.813961676418,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_korean_elo_votes","value":1440,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_korean_elo_interval","value":19.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_korean_elo","value":1170.029703631397,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_korean_elo_votes","value":751,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_korean_elo_interval","value":24.27,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_korean_elo","value":1162.5096204405156,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_korean_elo_votes","value":152,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_korean_elo_interval","value":50.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_korean_elo","value":1150.9273331669506,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_korean_elo_votes","value":319,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_korean_elo_interval","value":33.08,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_korean_elo","value":1142.593990649968,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_korean_elo_votes","value":857,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_korean_elo_interval","value":21.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_korean_elo","value":1140.4560085713538,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_korean_elo_votes","value":873,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_korean_elo_interval","value":23.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_korean_elo","value":1052.7631568508612,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_korean_elo_votes","value":802,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_korean_elo_interval","value":24.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_french_elo","value":1527.2731046730062,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_french_elo_votes","value":497,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_french_elo_interval","value":27.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_french_elo","value":1519.5205902652503,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_french_elo_votes","value":2058,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_french_elo_interval","value":14.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_french_elo","value":1518.8248955602637,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_french_elo_votes","value":549,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_french_elo_interval","value":26.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_french_elo","value":1512.8228011356425,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_french_elo_votes","value":2652,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_french_elo_interval","value":13.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_french_elo","value":1505.2613341055414,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_french_elo_votes","value":284,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_french_elo_interval","value":35.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_french_elo","value":1503.5911096311638,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_french_elo_votes","value":1430,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_french_elo_interval","value":17.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_french_elo","value":1502.9692078075304,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_french_elo_votes","value":2295,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_french_elo_interval","value":14.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_french_elo","value":1502.4730257771616,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_french_elo_votes","value":1150,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_french_elo_interval","value":18.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_french_elo","value":1502.404683988587,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_french_elo_votes","value":292,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_french_elo_interval","value":35.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_french_elo","value":1502.0764005203753,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_french_elo_votes","value":969,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_french_elo_interval","value":19.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_french_elo","value":1501.9577772296127,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_french_elo_votes","value":844,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_french_elo_interval","value":21.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_french_elo","value":1496.8652866604855,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_french_elo_votes","value":259,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_french_elo_interval","value":35.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_french_elo","value":1494.0124399031558,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_french_elo_votes","value":286,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_french_elo_interval","value":36.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_french_elo","value":1493.0097408094593,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_french_elo_votes","value":1434,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_french_elo_interval","value":17.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_french_elo","value":1492.791487015507,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_french_elo_votes","value":2395,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_french_elo_interval","value":13.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_french_elo","value":1491.6853953395876,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_french_elo_votes","value":1268,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_french_elo_interval","value":18.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_french_elo","value":1490.1428834348617,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_french_elo_votes","value":1186,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_french_elo_interval","value":18.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_french_elo","value":1489.5161711737017,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_french_elo_votes","value":1544,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_french_elo_interval","value":16.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_french_elo","value":1488.0855697340783,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_french_elo_votes","value":2791,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_french_elo_interval","value":13.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_french_elo","value":1488.017040098256,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_french_elo_votes","value":1216,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_french_elo_interval","value":18.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_french_elo","value":1486.4001835047686,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_french_elo_votes","value":4197,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_french_elo_interval","value":11.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_french_elo","value":1484.7233583571985,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_french_elo_votes","value":2512,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_french_elo_interval","value":13.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_french_elo","value":1481.0541541732002,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_french_elo_votes","value":2188,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_french_elo_interval","value":14.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_french_elo","value":1474.4590903910535,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_french_elo_votes","value":1298,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_french_elo_interval","value":17.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_french_elo","value":1472.7298241774367,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_french_elo_votes","value":2211,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_french_elo_interval","value":14.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_french_elo","value":1472.3841910942365,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_french_elo_votes","value":2391,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_french_elo_interval","value":13.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_french_elo","value":1471.9787228044015,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_french_elo_votes","value":1613,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_french_elo_interval","value":16.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_french_elo","value":1471.8182986071583,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_french_elo_votes","value":2245,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_french_elo_interval","value":14.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_french_elo","value":1471.6928139707238,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_french_elo_votes","value":1576,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_french_elo_interval","value":16.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_french_elo","value":1471.5941332769069,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_french_elo_votes","value":424,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_french_elo_interval","value":30.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_french_elo","value":1470.7703006999407,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_french_elo_votes","value":2026,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_french_elo_interval","value":14.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_french_elo","value":1469.0916048305676,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_french_elo_votes","value":1372,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_french_elo_interval","value":17.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_french_elo","value":1468.1897490073457,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_french_elo_votes","value":791,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_french_elo_interval","value":21.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_french_elo","value":1464.916887639664,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_french_elo_votes","value":2284,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_french_elo_interval","value":14.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_french_elo","value":1463.7615173890058,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_french_elo_votes","value":1635,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_french_elo_interval","value":16.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_french_elo","value":1461.3891244070721,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_french_elo_votes","value":3026,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_french_elo_interval","value":12.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_french_elo","value":1459.684286354974,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_french_elo_votes","value":262,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_french_elo_interval","value":36.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_french_elo","value":1459.21486167162,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_french_elo_votes","value":706,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_french_elo_interval","value":22.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_french_elo","value":1458.4876165347055,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_french_elo_votes","value":2001,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_french_elo_interval","value":14.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_french_elo","value":1457.8942383859305,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_french_elo_votes","value":1348,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_french_elo_interval","value":17.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_french_elo","value":1456.9239781184692,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_french_elo_votes","value":840,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_french_elo_interval","value":21.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_french_elo","value":1456.5873380200833,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_french_elo_votes","value":1274,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_french_elo_interval","value":18.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_french_elo","value":1455.2498524026853,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_french_elo_votes","value":912,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_french_elo_interval","value":20.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_french_elo","value":1454.3357610194043,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_french_elo_votes","value":1852,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_french_elo_interval","value":15.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_french_elo","value":1454.32916438473,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_french_elo_votes","value":1440,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_french_elo_interval","value":16.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_french_elo","value":1454.2245067836104,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_french_elo_votes","value":483,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_french_elo_interval","value":28.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_french_elo","value":1453.6645289704036,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_french_elo_votes","value":1281,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_french_elo_interval","value":17.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_french_elo","value":1451.714428301564,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_french_elo_votes","value":262,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_french_elo_interval","value":39.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_french_elo","value":1450.8218921524667,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_french_elo_votes","value":1100,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_french_elo_interval","value":19.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_french_elo","value":1449.9776208195694,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_french_elo_votes","value":944,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_french_elo_interval","value":19.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_french_elo","value":1448.7878938761698,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_french_elo_votes","value":452,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_french_elo_interval","value":29.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_french_elo","value":1447.315901779775,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_french_elo_votes","value":1827,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_french_elo_interval","value":15.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_french_elo","value":1446.3636913185119,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_french_elo_votes","value":289,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_french_elo_interval","value":35.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_french_elo","value":1444.8044027826638,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_french_elo_votes","value":2295,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_french_elo_interval","value":14.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_french_elo","value":1444.3877362096437,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_french_elo_votes","value":2166,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_french_elo_interval","value":13.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_french_elo","value":1443.600441809626,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_french_elo_votes","value":419,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_french_elo_interval","value":29.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_french_elo","value":1442.7620066305099,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_french_elo_votes","value":385,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_french_elo_interval","value":30.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_french_elo","value":1442.3012135843085,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_french_elo_votes","value":921,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_french_elo_interval","value":20.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_french_elo","value":1440.2936685032666,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_french_elo_votes","value":2227,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_french_elo_interval","value":14.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_french_elo","value":1439.02407948367,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_french_elo_votes","value":2004,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_french_elo_interval","value":14.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_french_elo","value":1435.3202189117105,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_french_elo_votes","value":269,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_french_elo_interval","value":34.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_french_elo","value":1433.2777409136186,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_french_elo_votes","value":227,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_french_elo_interval","value":39.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_french_elo","value":1432.6823283422093,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_french_elo_votes","value":1030,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_french_elo_interval","value":19.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_french_elo","value":1432.00374585218,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_french_elo_votes","value":2617,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_french_elo_interval","value":12.6,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_french_elo","value":1431.5790818528587,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_french_elo_votes","value":306,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_french_elo_interval","value":33.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_french_elo","value":1430.0552894635018,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_french_elo_votes","value":826,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_french_elo_interval","value":22.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_french_elo","value":1428.739732054344,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_french_elo_votes","value":1243,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_french_elo_interval","value":17.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_french_elo","value":1427.4494758617896,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_french_elo_votes","value":1416,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_french_elo_interval","value":16.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_french_elo","value":1423.5929288618786,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_french_elo_votes","value":2117,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_french_elo_interval","value":14.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_french_elo","value":1422.8817432571693,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_french_elo_votes","value":3208,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_french_elo_interval","value":12.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_french_elo","value":1420.866970553153,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_french_elo_votes","value":2051,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_french_elo_interval","value":14.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_french_elo","value":1418.957144618593,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_french_elo_votes","value":340,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_french_elo_interval","value":31.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_french_elo","value":1418.830113755446,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_french_elo_votes","value":336,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_french_elo_interval","value":32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_french_elo","value":1417.010098024154,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_french_elo_votes","value":237,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_french_elo_interval","value":37.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_french_elo","value":1413.413254532946,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_french_elo_votes","value":388,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_french_elo_interval","value":30.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_french_elo","value":1412.4101268357404,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_french_elo_votes","value":2267,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_french_elo_interval","value":14.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_french_elo","value":1411.8010561058472,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_french_elo_votes","value":2581,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_french_elo_interval","value":13.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_french_elo","value":1411.7339943946354,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_french_elo_votes","value":888,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_french_elo_interval","value":20.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_french_elo","value":1409.1044877946108,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_french_elo_votes","value":4213,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_french_elo_interval","value":11.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_french_elo","value":1409.0601292090855,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_french_elo_votes","value":433,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_french_elo_interval","value":28.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_french_elo","value":1408.4589596346407,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_french_elo_votes","value":848,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_french_elo_interval","value":21.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_french_elo","value":1403.1720676428763,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_french_elo_votes","value":279,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_french_elo_interval","value":34.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_french_elo","value":1399.1737669050922,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_french_elo_votes","value":520,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_french_elo_interval","value":27.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_french_elo","value":1397.6105484298193,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_french_elo_votes","value":449,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_french_elo_interval","value":29.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_french_elo","value":1395.5633583435263,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_french_elo_votes","value":2092,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_french_elo_interval","value":14.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_french_elo","value":1395.0730218609335,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_french_elo_votes","value":646,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_french_elo_interval","value":24.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_french_elo","value":1386.061516795774,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_french_elo_votes","value":413,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_french_elo_interval","value":29.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_french_elo","value":1385.042845656644,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_french_elo_votes","value":594,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_french_elo_interval","value":24.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_french_elo","value":1381.8982464782048,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_french_elo_votes","value":742,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_french_elo_interval","value":22.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_french_elo","value":1380.5723554992867,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_french_elo_votes","value":267,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_french_elo_interval","value":36.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_french_elo","value":1370.1165985798777,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_french_elo_votes","value":474,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_french_elo_interval","value":26.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_french_elo","value":1368.5563875837545,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_french_elo_votes","value":460,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_french_elo_interval","value":27.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_french_elo","value":1368.1313107934284,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_french_elo_votes","value":657,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_french_elo_interval","value":23.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_french_elo","value":1364.8683704873254,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_french_elo_votes","value":1039,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_french_elo_interval","value":20.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_french_elo","value":1363.341014110303,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_french_elo_votes","value":614,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_french_elo_interval","value":24.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_french_elo","value":1362.7402549956903,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_french_elo_votes","value":1303,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_french_elo_interval","value":17.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_french_elo","value":1357.7122847263595,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_french_elo_votes","value":582,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_french_elo_interval","value":25.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_french_elo","value":1352.6333601839851,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_french_elo_votes","value":217,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_french_elo_interval","value":39.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_french_elo","value":1351.6982802445555,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_french_elo_votes","value":352,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_french_elo_interval","value":30.27,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_french_elo","value":1351.0690507103282,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_french_elo_votes","value":776,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_french_elo_interval","value":22.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_french_elo","value":1343.9075852108967,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_french_elo_votes","value":252,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_french_elo_interval","value":36.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_french_elo","value":1335.3672865325202,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_french_elo_votes","value":135,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_french_elo_interval","value":54.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_french_elo","value":1333.9546275793437,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_french_elo_votes","value":203,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_french_elo_interval","value":44.27,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_french_elo","value":1331.9876356670127,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_french_elo_votes","value":261,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_french_elo_interval","value":36.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_french_elo","value":1311.2489385910465,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_french_elo_votes","value":709,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_french_elo_interval","value":22.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_french_elo","value":1304.124697828816,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_french_elo_votes","value":1359,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_french_elo_interval","value":21.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_french_elo","value":1296.8095196012928,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_french_elo_votes","value":649,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_french_elo_interval","value":24.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_french_elo","value":1282.3688676611025,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_french_elo_votes","value":427,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_french_elo_interval","value":29.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_french_elo","value":1281.4771709762233,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_french_elo_votes","value":575,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_french_elo_interval","value":25.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_french_elo","value":1280.2337590821253,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_french_elo_votes","value":340,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_french_elo_interval","value":32.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_french_elo","value":1273.017145225227,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_french_elo_votes","value":441,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_french_elo_interval","value":29.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_french_elo","value":1272.6074984466036,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_french_elo_votes","value":457,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_french_elo_interval","value":29.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_french_elo","value":1262.8375429565795,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_french_elo_votes","value":457,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_french_elo_interval","value":28.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_french_elo","value":1261.2965214324702,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_french_elo_votes","value":501,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_french_elo_interval","value":28.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_french_elo","value":1259.4059244596751,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_french_elo_votes","value":596,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_french_elo_interval","value":25.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_french_elo","value":1247.435730623864,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_french_elo_votes","value":793,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_french_elo_interval","value":23.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_french_elo","value":1224.1938970009994,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_french_elo_votes","value":205,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_french_elo_interval","value":39.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_french_elo","value":1203.3035453608275,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_french_elo_votes","value":142,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_french_elo_interval","value":49.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_french_elo","value":1177.48187774273,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_french_elo_votes","value":478,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_french_elo_interval","value":29.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_spanish_elo","value":1520.5391480969076,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_spanish_elo_votes","value":474,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_spanish_elo_interval","value":26.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_spanish_elo","value":1519.4728235042633,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_spanish_elo_votes","value":942,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_spanish_elo_interval","value":20.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_spanish_elo","value":1519.004853846378,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_spanish_elo_votes","value":294,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_spanish_elo_interval","value":33.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_spanish_elo","value":1510.1354553203273,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_spanish_elo_votes","value":2844,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_spanish_elo_interval","value":12.36,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_spanish_elo","value":1504.4159507118413,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_spanish_elo_votes","value":225,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_spanish_elo_interval","value":38.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_spanish_elo","value":1495.7657704660926,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_spanish_elo_votes","value":1314,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_spanish_elo_interval","value":17.08,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_spanish_elo","value":1495.53226419919,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_spanish_elo_votes","value":554,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_spanish_elo_interval","value":25.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_spanish_elo","value":1494.6351064846717,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_spanish_elo_votes","value":2051,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_spanish_elo_interval","value":14.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_spanish_elo","value":1491.7017190432998,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_spanish_elo_votes","value":875,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_spanish_elo_interval","value":20.6,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_spanish_elo","value":1490.7638243319184,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_spanish_elo_votes","value":862,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_spanish_elo_interval","value":20.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_spanish_elo","value":1488.3724988064043,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_spanish_elo_votes","value":262,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_spanish_elo_interval","value":35.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_spanish_elo","value":1485.7095039526973,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_spanish_elo_votes","value":1285,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_spanish_elo_interval","value":17.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_spanish_elo","value":1479.7127312428947,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_spanish_elo_votes","value":4053,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_spanish_elo_interval","value":10.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_spanish_elo","value":1479.6322885149923,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_spanish_elo_votes","value":1430,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_spanish_elo_interval","value":16.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_spanish_elo","value":1476.3398003321288,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_spanish_elo_votes","value":1258,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_spanish_elo_interval","value":17.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_spanish_elo","value":1475.9480936148132,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_spanish_elo_votes","value":950,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_spanish_elo_interval","value":20.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_spanish_elo","value":1473.4745697386488,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_spanish_elo_votes","value":3451,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_spanish_elo_interval","value":11.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_spanish_elo","value":1470.794981861114,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_spanish_elo_votes","value":1004,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_spanish_elo_interval","value":18.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_spanish_elo","value":1469.5350597250265,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_spanish_elo_votes","value":2320,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_spanish_elo_interval","value":13.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_spanish_elo","value":1468.5446999624578,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_spanish_elo_votes","value":2067,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_spanish_elo_interval","value":13.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_spanish_elo","value":1468.080385240993,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_spanish_elo_votes","value":1945,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_spanish_elo_interval","value":14.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_spanish_elo","value":1464.9927883604041,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_spanish_elo_votes","value":1865,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_spanish_elo_interval","value":14.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_spanish_elo","value":1464.7306735827756,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_spanish_elo_votes","value":1325,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_spanish_elo_interval","value":16.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_spanish_elo","value":1463.7351335669805,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_spanish_elo_votes","value":2168,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_spanish_elo_interval","value":13.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_spanish_elo","value":1463.6836964217377,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_spanish_elo_votes","value":1367,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_spanish_elo_interval","value":16.6,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_spanish_elo","value":1457.7369317026134,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_spanish_elo_votes","value":437,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_spanish_elo_interval","value":27.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_spanish_elo","value":1457.603057566837,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_spanish_elo_votes","value":2499,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_spanish_elo_interval","value":12.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_spanish_elo","value":1457.0631161677643,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_spanish_elo_votes","value":1245,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_spanish_elo_interval","value":17.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_spanish_elo","value":1456.2517460114407,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_spanish_elo_votes","value":1731,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_spanish_elo_interval","value":15.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_spanish_elo","value":1455.483882498233,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_spanish_elo_votes","value":416,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_spanish_elo_interval","value":28.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_spanish_elo","value":1454.1892145812383,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_spanish_elo_votes","value":678,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_spanish_elo_interval","value":23.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_spanish_elo","value":1453.532167718679,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_spanish_elo_votes","value":1127,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_spanish_elo_interval","value":17.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_spanish_elo","value":1453.153699560751,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_spanish_elo_votes","value":2060,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_spanish_elo_interval","value":14.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_spanish_elo","value":1452.5283965626502,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_spanish_elo_votes","value":2162,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_spanish_elo_interval","value":13.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_spanish_elo","value":1451.2503748210431,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_spanish_elo_votes","value":1081,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_spanish_elo_interval","value":18.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_spanish_elo","value":1450.2955837016823,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_spanish_elo_votes","value":301,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_spanish_elo_interval","value":35.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_spanish_elo","value":1450.1800496210637,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_spanish_elo_votes","value":244,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_spanish_elo_interval","value":36.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_spanish_elo","value":1449.932954592668,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_spanish_elo_votes","value":1320,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_spanish_elo_interval","value":16.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_spanish_elo","value":1448.2387115856125,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_spanish_elo_votes","value":2301,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_spanish_elo_interval","value":13.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_spanish_elo","value":1446.9578978823731,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_spanish_elo_votes","value":1269,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_spanish_elo_interval","value":17.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_spanish_elo","value":1446.2180868521996,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_spanish_elo_votes","value":272,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_spanish_elo_interval","value":33.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_spanish_elo","value":1445.7922890260227,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_spanish_elo_votes","value":1196,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_spanish_elo_interval","value":17.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_spanish_elo","value":1443.3678637872645,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_spanish_elo_votes","value":746,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_spanish_elo_interval","value":21.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_spanish_elo","value":1443.3573541552098,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_spanish_elo_votes","value":253,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_spanish_elo_interval","value":35.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_spanish_elo","value":1443.0717601343224,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_spanish_elo_votes","value":249,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_spanish_elo_interval","value":37.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_spanish_elo","value":1440.9850817393772,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_spanish_elo_votes","value":963,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_spanish_elo_interval","value":19.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_spanish_elo","value":1440.5934446491387,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_spanish_elo_votes","value":1179,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_spanish_elo_interval","value":17.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_spanish_elo","value":1440.5317525542437,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_spanish_elo_votes","value":2935,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_spanish_elo_interval","value":11.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_spanish_elo","value":1440.0702183129538,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_spanish_elo_votes","value":354,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_spanish_elo_interval","value":30.89,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_spanish_elo","value":1437.2368583938928,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_spanish_elo_votes","value":1400,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_spanish_elo_interval","value":16.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_spanish_elo","value":1435.9716096236418,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_spanish_elo_votes","value":1015,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_spanish_elo_interval","value":18.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_spanish_elo","value":1435.532839563866,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_spanish_elo_votes","value":1578,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_spanish_elo_interval","value":15.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_spanish_elo","value":1435.044483617228,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_spanish_elo_votes","value":687,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_spanish_elo_interval","value":23.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_spanish_elo","value":1434.271399881475,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_spanish_elo_votes","value":345,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_spanish_elo_interval","value":30.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_spanish_elo","value":1432.6332794725104,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_spanish_elo_votes","value":1211,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_spanish_elo_interval","value":17.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_spanish_elo","value":1432.376411712123,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_spanish_elo_votes","value":1959,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_spanish_elo_interval","value":14.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_spanish_elo","value":1431.8389977429006,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_spanish_elo_votes","value":1578,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_spanish_elo_interval","value":15.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_spanish_elo","value":1429.5297261210742,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_spanish_elo_votes","value":2911,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_spanish_elo_interval","value":11.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_spanish_elo","value":1428.0384114836893,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_spanish_elo_votes","value":460,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_spanish_elo_interval","value":28.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_spanish_elo","value":1423.9705645123684,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_spanish_elo_votes","value":965,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_spanish_elo_interval","value":18.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_spanish_elo","value":1422.914305722932,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_spanish_elo_votes","value":1531,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_spanish_elo_interval","value":15.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_spanish_elo","value":1421.514088308671,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_spanish_elo_votes","value":966,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_spanish_elo_interval","value":19.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_spanish_elo","value":1421.2580117751136,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_spanish_elo_votes","value":3454,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_spanish_elo_interval","value":10.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_spanish_elo","value":1421.0984064967274,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_spanish_elo_votes","value":4363,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_spanish_elo_interval","value":10.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_spanish_elo","value":1421.0634352962813,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_spanish_elo_votes","value":2010,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_spanish_elo_interval","value":13.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_spanish_elo","value":1418.5705942451086,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_spanish_elo_votes","value":2012,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_spanish_elo_interval","value":13.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_spanish_elo","value":1417.0706932837854,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_spanish_elo_votes","value":203,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_spanish_elo_interval","value":41.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_spanish_elo","value":1416.708720415464,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_spanish_elo_votes","value":354,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_spanish_elo_interval","value":30.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_spanish_elo","value":1414.6595304313676,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_spanish_elo_votes","value":1440,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_spanish_elo_interval","value":16.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_spanish_elo","value":1413.1208227937705,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_spanish_elo_votes","value":1536,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_spanish_elo_interval","value":15.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_spanish_elo","value":1411.3704032041696,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_spanish_elo_votes","value":261,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_spanish_elo_interval","value":35.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_spanish_elo","value":1410.7683664773122,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_spanish_elo_votes","value":389,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_spanish_elo_interval","value":31.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_spanish_elo","value":1407.0866449408804,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_spanish_elo_votes","value":939,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_spanish_elo_interval","value":19.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_spanish_elo","value":1406.3295158777125,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_spanish_elo_votes","value":643,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_spanish_elo_interval","value":23.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_spanish_elo","value":1404.7376721949865,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_spanish_elo_votes","value":422,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_spanish_elo_interval","value":28.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_spanish_elo","value":1404.4720675495016,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_spanish_elo_votes","value":1906,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_spanish_elo_interval","value":14.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_spanish_elo","value":1403.7138747244148,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_spanish_elo_votes","value":789,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_spanish_elo_interval","value":21.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_spanish_elo","value":1403.4171294062824,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_spanish_elo_votes","value":715,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_spanish_elo_interval","value":22.36,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_spanish_elo","value":1402.0348532207029,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_spanish_elo_votes","value":2710,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_spanish_elo_interval","value":12.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_spanish_elo","value":1399.7358647682652,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_spanish_elo_votes","value":2052,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_spanish_elo_interval","value":14.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_spanish_elo","value":1398.9922560519028,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_spanish_elo_votes","value":2009,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_spanish_elo_interval","value":14.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_spanish_elo","value":1398.8503080495582,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_spanish_elo_votes","value":900,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_spanish_elo_interval","value":20.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_spanish_elo","value":1394.749725416619,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_spanish_elo_votes","value":1221,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_spanish_elo_interval","value":17.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_spanish_elo","value":1390.918306504259,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_spanish_elo_votes","value":1003,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_spanish_elo_interval","value":19.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_spanish_elo","value":1388.704857353369,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_spanish_elo_votes","value":855,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_spanish_elo_interval","value":21.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_spanish_elo","value":1388.5570374917363,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_spanish_elo_votes","value":185,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_spanish_elo_interval","value":41.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_spanish_elo","value":1385.4464488348985,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_spanish_elo_votes","value":824,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_spanish_elo_interval","value":20.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_spanish_elo","value":1375.7813753715918,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_spanish_elo_votes","value":1132,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_spanish_elo_interval","value":18.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_spanish_elo","value":1372.6065033619407,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_spanish_elo_votes","value":232,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_spanish_elo_interval","value":39.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_spanish_elo","value":1370.600447599138,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_spanish_elo_votes","value":1914,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_spanish_elo_interval","value":14.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_spanish_elo","value":1360.2876288847474,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_spanish_elo_votes","value":237,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_spanish_elo_interval","value":39.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_spanish_elo","value":1359.9989593648595,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_spanish_elo_votes","value":686,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_spanish_elo_interval","value":23.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_spanish_elo","value":1357.919445045963,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_spanish_elo_votes","value":987,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_spanish_elo_interval","value":19.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_spanish_elo","value":1357.58986708131,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_spanish_elo_votes","value":456,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_spanish_elo_interval","value":28.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_spanish_elo","value":1354.7527155255216,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_spanish_elo_votes","value":855,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_spanish_elo_interval","value":20.89,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_spanish_elo","value":1354.0164826397797,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_spanish_elo_votes","value":1475,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_spanish_elo_interval","value":16.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_spanish_elo","value":1353.1215454290252,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_spanish_elo_votes","value":835,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_spanish_elo_interval","value":20.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_spanish_elo","value":1350.151782105275,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_spanish_elo_votes","value":439,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_spanish_elo_interval","value":28.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_spanish_elo","value":1348.8735606425073,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_spanish_elo_votes","value":893,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_spanish_elo_interval","value":20.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_spanish_elo","value":1347.3402029148683,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_spanish_elo_votes","value":1179,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_spanish_elo_interval","value":17.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_spanish_elo","value":1346.7045407984867,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_spanish_elo_votes","value":997,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_spanish_elo_interval","value":19.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_spanish_elo","value":1345.0039987566713,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_spanish_elo_votes","value":142,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_spanish_elo_interval","value":48.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_spanish_elo","value":1335.5347868821252,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_spanish_elo_votes","value":186,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_spanish_elo_interval","value":44.89,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_spanish_elo","value":1326.7112514892997,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_spanish_elo_votes","value":943,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_spanish_elo_interval","value":20.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_spanish_elo","value":1326.2558355459985,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_spanish_elo_votes","value":206,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_spanish_elo_interval","value":42.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_spanish_elo","value":1321.1128390102554,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_spanish_elo_votes","value":126,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_spanish_elo_interval","value":50.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_spanish_elo","value":1319.0626322696403,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_spanish_elo_votes","value":805,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_spanish_elo_interval","value":21.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_spanish_elo","value":1316.8368429188251,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_spanish_elo_votes","value":481,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_spanish_elo_interval","value":27.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_spanish_elo","value":1309.5072340224572,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_spanish_elo_votes","value":918,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_spanish_elo_interval","value":20.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_spanish_elo","value":1293.1031922426591,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_spanish_elo_votes","value":820,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_spanish_elo_interval","value":21.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_spanish_elo","value":1292.0823763714145,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_spanish_elo_votes","value":1712,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_spanish_elo_interval","value":20.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_spanish_elo","value":1283.589951561029,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_spanish_elo_votes","value":809,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_spanish_elo_interval","value":21.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_spanish_elo","value":1277.761805049875,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_spanish_elo_votes","value":710,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_spanish_elo_interval","value":23.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_spanish_elo","value":1276.0469654254118,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_spanish_elo_votes","value":741,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_spanish_elo_interval","value":23.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_spanish_elo","value":1269.4710447769187,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_spanish_elo_votes","value":636,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_spanish_elo_interval","value":24.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_spanish_elo","value":1268.8316966345585,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_spanish_elo_votes","value":546,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_spanish_elo_interval","value":27.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_spanish_elo","value":1267.3711430591427,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_spanish_elo_votes","value":284,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_spanish_elo_interval","value":38.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_spanish_elo","value":1255.3900334839332,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_spanish_elo_votes","value":347,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_spanish_elo_interval","value":30.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_spanish_elo","value":1253.0287777485164,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_spanish_elo_votes","value":606,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_spanish_elo_interval","value":25.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_spanish_elo","value":1236.2259458893427,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_spanish_elo_votes","value":584,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_spanish_elo_interval","value":25.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_spanish_elo","value":1234.1944864369332,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_spanish_elo_votes","value":127,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_spanish_elo_interval","value":51.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_spanish_elo","value":1228.184044873137,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_spanish_elo_votes","value":845,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_spanish_elo_interval","value":22.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_spanish_elo","value":1169.177038462915,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_spanish_elo_votes","value":565,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_spanish_elo_interval","value":27.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_russian_elo","value":1533.955340668706,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_russian_elo_votes","value":671,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_russian_elo_interval","value":22.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_russian_elo","value":1519.8536737018212,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_russian_elo_votes","value":458,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_russian_elo_interval","value":27.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_russian_elo","value":1519.1110489468488,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_russian_elo_votes","value":1089,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_russian_elo_interval","value":18.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_russian_elo","value":1518.6392357635718,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_russian_elo_votes","value":1902,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_russian_elo_interval","value":14.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_russian_elo","value":1518.1739173123815,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_russian_elo_votes","value":3394,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_russian_elo_interval","value":10.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_russian_elo","value":1514.3988808293946,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_russian_elo_votes","value":4787,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_russian_elo_interval","value":9.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_russian_elo","value":1507.1711954821124,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_russian_elo_votes","value":3918,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_russian_elo_interval","value":10.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_russian_elo","value":1502.995568676571,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_russian_elo_votes","value":4719,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_russian_elo_interval","value":9.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_russian_elo","value":1496.7139085564042,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_russian_elo_votes","value":14555,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_russian_elo_interval","value":5.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_russian_elo","value":1496.0821674407782,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_russian_elo_votes","value":9363,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_russian_elo_interval","value":6.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_russian_elo","value":1494.4445925187795,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_russian_elo_votes","value":6866,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_russian_elo_interval","value":8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_russian_elo","value":1492.431099695128,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_russian_elo_votes","value":5474,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_russian_elo_interval","value":8.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_russian_elo","value":1487.982239190359,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_russian_elo_votes","value":4166,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_russian_elo_interval","value":9.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_russian_elo","value":1487.9314833224475,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_russian_elo_votes","value":2291,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_russian_elo_interval","value":12.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_russian_elo","value":1486.727820705753,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_russian_elo_votes","value":1028,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_russian_elo_interval","value":18.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_russian_elo","value":1481.837431244935,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_russian_elo_votes","value":5001,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_russian_elo_interval","value":8.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_russian_elo","value":1481.711407868369,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_russian_elo_votes","value":3656,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_russian_elo_interval","value":10.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_russian_elo","value":1481.1322146996906,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_russian_elo_votes","value":4092,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_russian_elo_interval","value":9.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_russian_elo","value":1480.135888189043,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_russian_elo_votes","value":7202,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_russian_elo_interval","value":7.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_russian_elo","value":1479.9191701177879,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_russian_elo_votes","value":583,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_russian_elo_interval","value":23.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_russian_elo","value":1473.9780092623669,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_russian_elo_votes","value":7149,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_russian_elo_interval","value":7.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_russian_elo","value":1472.8913977858545,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_russian_elo_votes","value":7412,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_russian_elo_interval","value":7.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_russian_elo","value":1470.3678178667958,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_russian_elo_votes","value":4774,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_russian_elo_interval","value":9.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_russian_elo","value":1464.7521903778254,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_russian_elo_votes","value":4598,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_russian_elo_interval","value":9.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_russian_elo","value":1460.7169589650346,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_russian_elo_votes","value":827,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_russian_elo_interval","value":19.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_russian_elo","value":1460.4170723264738,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_russian_elo_votes","value":12211,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_russian_elo_interval","value":5.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_russian_elo","value":1457.9366934699685,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_russian_elo_votes","value":4669,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_russian_elo_interval","value":9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_russian_elo","value":1453.8574315267301,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_russian_elo_votes","value":7504,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_russian_elo_interval","value":7.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_russian_elo","value":1452.462637066323,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_russian_elo_votes","value":6319,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_russian_elo_interval","value":8.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_russian_elo","value":1452.2193955252576,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_russian_elo_votes","value":4920,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_russian_elo_interval","value":8.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_russian_elo","value":1450.279386191857,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_russian_elo_votes","value":9048,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_russian_elo_interval","value":6.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_russian_elo","value":1449.7261725544881,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_russian_elo_votes","value":5671,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_russian_elo_interval","value":8.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_russian_elo","value":1449.0788208060071,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_russian_elo_votes","value":4639,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_russian_elo_interval","value":9.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_russian_elo","value":1447.37628449801,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_russian_elo_votes","value":9053,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_russian_elo_interval","value":6.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_russian_elo","value":1446.2313031971373,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_russian_elo_votes","value":4252,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_russian_elo_interval","value":9.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_russian_elo","value":1445.1641595654041,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_russian_elo_votes","value":955,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_russian_elo_interval","value":19.08,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_russian_elo","value":1443.3285466069854,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_russian_elo_votes","value":4098,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_russian_elo_interval","value":9.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_russian_elo","value":1439.3862580012903,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_russian_elo_votes","value":7983,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_russian_elo_interval","value":7.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_russian_elo","value":1436.3478359338271,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_russian_elo_votes","value":9580,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_russian_elo_interval","value":6.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_russian_elo","value":1436.2831316724646,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_russian_elo_votes","value":3447,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_russian_elo_interval","value":9.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_russian_elo","value":1435.3163870291817,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_russian_elo_votes","value":5211,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_russian_elo_interval","value":8.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_russian_elo","value":1434.1747985386314,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_russian_elo_votes","value":5266,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_russian_elo_interval","value":8.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_russian_elo","value":1433.9158436723028,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_russian_elo_votes","value":1043,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_russian_elo_interval","value":17.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_russian_elo","value":1433.5219385829835,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_russian_elo_votes","value":898,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_russian_elo_interval","value":18.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_russian_elo","value":1432.1692469036534,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_russian_elo_votes","value":1115,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_russian_elo_interval","value":17.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_russian_elo","value":1431.221858573149,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_russian_elo_votes","value":1516,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_russian_elo_interval","value":15.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_russian_elo","value":1429.4443393546303,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_russian_elo_votes","value":4822,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_russian_elo_interval","value":9.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_russian_elo","value":1429.3079594743594,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_russian_elo_votes","value":10715,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_russian_elo_interval","value":6.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_russian_elo","value":1427.7360788188294,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_russian_elo_votes","value":4732,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_russian_elo_interval","value":9.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_russian_elo","value":1427.04293699345,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_russian_elo_votes","value":5745,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_russian_elo_interval","value":8.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_russian_elo","value":1426.720567290734,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_russian_elo_votes","value":7506,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_russian_elo_interval","value":7.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_russian_elo","value":1423.282854802514,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_russian_elo_votes","value":6096,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_russian_elo_interval","value":7.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_russian_elo","value":1422.8995389963604,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_russian_elo_votes","value":1645,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_russian_elo_interval","value":13.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_russian_elo","value":1422.8866290620795,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_russian_elo_votes","value":1523,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_russian_elo_interval","value":14.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_russian_elo","value":1422.3594801548993,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_russian_elo_votes","value":305,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_russian_elo_interval","value":30.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_russian_elo","value":1421.9862825154496,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_russian_elo_votes","value":953,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_russian_elo_interval","value":18.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_russian_elo","value":1421.8248627524815,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_russian_elo_votes","value":7233,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_russian_elo_interval","value":7.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_russian_elo","value":1421.7889223113255,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_russian_elo_votes","value":3634,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_russian_elo_interval","value":10.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_russian_elo","value":1419.7506149334172,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_russian_elo_votes","value":7187,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_russian_elo_interval","value":7.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_russian_elo","value":1418.5602553480064,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_russian_elo_votes","value":3546,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_russian_elo_interval","value":9.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_russian_elo","value":1417.0998385723826,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_russian_elo_votes","value":6983,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_russian_elo_interval","value":7.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_russian_elo","value":1416.0052109829942,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_russian_elo_votes","value":2983,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_russian_elo_interval","value":11.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_russian_elo","value":1415.0759007528882,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_russian_elo_votes","value":9726,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_russian_elo_interval","value":6.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_russian_elo","value":1414.7045849254578,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_russian_elo_votes","value":12290,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_russian_elo_interval","value":5.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_russian_elo","value":1412.8178215044616,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_russian_elo_votes","value":1570,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_russian_elo_interval","value":14.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_russian_elo","value":1410.8551583169979,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_russian_elo_votes","value":10181,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_russian_elo_interval","value":5.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_russian_elo","value":1409.8225517322576,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_russian_elo_votes","value":1518,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_russian_elo_interval","value":15.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_russian_elo","value":1407.6253740716384,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_russian_elo_votes","value":883,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_russian_elo_interval","value":20.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_russian_elo","value":1406.5430927925715,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_russian_elo_votes","value":2173,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_russian_elo_interval","value":12.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_russian_elo","value":1406.266248804692,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_russian_elo_votes","value":4682,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_russian_elo_interval","value":8.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_russian_elo","value":1403.8615951810802,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_russian_elo_votes","value":1618,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_russian_elo_interval","value":14.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_russian_elo","value":1403.618532922965,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_russian_elo_votes","value":1173,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_russian_elo_interval","value":16.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_russian_elo","value":1399.9436772445997,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_russian_elo_votes","value":530,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_russian_elo_interval","value":23.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_russian_elo","value":1399.9182724010366,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_russian_elo_votes","value":1552,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_russian_elo_interval","value":14.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_russian_elo","value":1399.7915137816995,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_russian_elo_votes","value":3473,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_russian_elo_interval","value":10.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_russian_elo","value":1398.7348204492707,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_russian_elo_votes","value":7507,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_russian_elo_interval","value":7.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_russian_elo","value":1395.5853296130385,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_russian_elo_votes","value":5274,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_russian_elo_interval","value":8.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_russian_elo","value":1394.7459469664273,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_russian_elo_votes","value":1235,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_russian_elo_interval","value":17.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_russian_elo","value":1391.3560721243625,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_russian_elo_votes","value":3866,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_russian_elo_interval","value":10.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_russian_elo","value":1389.7889012823043,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_russian_elo_votes","value":3317,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_russian_elo_interval","value":10.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_russian_elo","value":1384.8075150211605,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_russian_elo_votes","value":7441,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_russian_elo_interval","value":7.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_russian_elo","value":1382.7612099623689,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_russian_elo_votes","value":10254,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_russian_elo_interval","value":6.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_russian_elo","value":1380.965100295095,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_russian_elo_votes","value":16646,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_russian_elo_interval","value":5.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_russian_elo","value":1379.608932032328,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_russian_elo_votes","value":7223,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_russian_elo_interval","value":7.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_russian_elo","value":1377.016791269607,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_russian_elo_votes","value":3630,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_russian_elo_interval","value":9.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_russian_elo","value":1376.9912931274068,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_russian_elo_votes","value":3810,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_russian_elo_interval","value":9.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_russian_elo","value":1373.1897885801213,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_russian_elo_votes","value":3573,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_russian_elo_interval","value":9.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_russian_elo","value":1372.9077014510008,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_russian_elo_votes","value":2005,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_russian_elo_interval","value":12.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_russian_elo","value":1369.2171073437003,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_russian_elo_votes","value":1564,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_russian_elo_interval","value":14.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_russian_elo","value":1366.22985421048,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_russian_elo_votes","value":1691,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_russian_elo_interval","value":14.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_russian_elo","value":1362.4162690130674,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_russian_elo_votes","value":6868,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_russian_elo_interval","value":7.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_russian_elo","value":1361.765801509639,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_russian_elo_votes","value":1872,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_russian_elo_interval","value":13.08,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_russian_elo","value":1358.519552596309,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_russian_elo_votes","value":5225,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_russian_elo_interval","value":8.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_russian_elo","value":1356.7218800219416,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_russian_elo_votes","value":2649,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_russian_elo_interval","value":12.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_russian_elo","value":1355.7312007802352,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_russian_elo_votes","value":3078,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_russian_elo_interval","value":10.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_russian_elo","value":1348.8850908106856,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_russian_elo_votes","value":3433,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_russian_elo_interval","value":9.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_russian_elo","value":1343.1566571584408,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_russian_elo_votes","value":2144,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_russian_elo_interval","value":12.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_russian_elo","value":1342.1676013905071,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_russian_elo_votes","value":1448,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_russian_elo_interval","value":15.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_russian_elo","value":1339.076258904852,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_russian_elo_votes","value":357,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_russian_elo_interval","value":29.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_russian_elo","value":1338.371071698446,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_russian_elo_votes","value":3292,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_russian_elo_interval","value":10.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_russian_elo","value":1337.328987595452,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_russian_elo_votes","value":929,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_russian_elo_interval","value":18.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_russian_elo","value":1335.5230929994505,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_russian_elo_votes","value":1019,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_russian_elo_interval","value":18.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_russian_elo","value":1335.3268850033423,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_russian_elo_votes","value":285,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_russian_elo_interval","value":31.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_russian_elo","value":1334.315751457072,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_russian_elo_votes","value":3429,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_russian_elo_interval","value":9.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_russian_elo","value":1332.3254223960257,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_russian_elo_votes","value":1716,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_russian_elo_interval","value":13.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_russian_elo","value":1330.4405842783353,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_russian_elo_votes","value":499,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_russian_elo_interval","value":25.6,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_russian_elo","value":1329.5839813458165,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_russian_elo_votes","value":2396,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_russian_elo_interval","value":11.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_russian_elo","value":1323.9175906230012,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_russian_elo_votes","value":3088,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_russian_elo_interval","value":10.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_russian_elo","value":1314.0859528625542,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_russian_elo_votes","value":4470,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_russian_elo_interval","value":8.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_russian_elo","value":1310.8511924003142,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_russian_elo_votes","value":412,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_russian_elo_interval","value":25.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_russian_elo","value":1304.1333831083332,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_russian_elo_votes","value":451,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_russian_elo_interval","value":27.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_russian_elo","value":1304.0275883507934,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_russian_elo_votes","value":1740,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_russian_elo_interval","value":13.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_russian_elo","value":1301.0667612422926,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_russian_elo_votes","value":4933,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_russian_elo_interval","value":8.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_russian_elo","value":1297.7083666686908,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_russian_elo_votes","value":395,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_russian_elo_interval","value":27.36,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_russian_elo","value":1295.8914201032203,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_russian_elo_votes","value":603,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_russian_elo_interval","value":23.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_russian_elo","value":1293.9126970760976,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_russian_elo_votes","value":307,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_russian_elo_interval","value":30.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_russian_elo","value":1290.8467316032093,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_russian_elo_votes","value":2224,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_russian_elo_interval","value":11.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_russian_elo","value":1286.1215514522682,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_russian_elo_votes","value":3103,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_russian_elo_interval","value":10.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_russian_elo","value":1285.513471921471,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_russian_elo_votes","value":13904,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_russian_elo_interval","value":7.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_russian_elo","value":1283.8035279541837,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_russian_elo_votes","value":334,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_russian_elo_interval","value":33.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_russian_elo","value":1278.19531370874,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_russian_elo_votes","value":756,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_russian_elo_interval","value":21.08,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_russian_elo","value":1275.26000978736,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_russian_elo_votes","value":8268,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_russian_elo_interval","value":7.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_russian_elo","value":1271.8489689237517,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_russian_elo_votes","value":5517,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_russian_elo_interval","value":8.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_russian_elo","value":1263.8875959360123,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_russian_elo_votes","value":5776,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_russian_elo_interval","value":8.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_russian_elo","value":1263.2622024590614,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_russian_elo_votes","value":2417,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_russian_elo_interval","value":11.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_russian_elo","value":1262.8673012498862,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_russian_elo_votes","value":2274,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_russian_elo_interval","value":12.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_russian_elo","value":1261.093427505338,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_russian_elo_votes","value":702,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_russian_elo_interval","value":20.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_russian_elo","value":1256.8595649314216,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_russian_elo_votes","value":5748,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_russian_elo_interval","value":8.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_russian_elo","value":1251.6661905321685,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_russian_elo_votes","value":5713,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_russian_elo_interval","value":7.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_russian_elo","value":1233.8503661559455,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_russian_elo_votes","value":9678,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_russian_elo_interval","value":7.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_russian_elo","value":1233.6420611216595,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_russian_elo_votes","value":7285,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_russian_elo_interval","value":8.08,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_russian_elo","value":1228.124835074305,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_russian_elo_votes","value":822,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_russian_elo_interval","value":18.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_russian_elo","value":1227.2701107345704,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_russian_elo_votes","value":1354,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_russian_elo_interval","value":15.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_russian_elo","value":1215.98077955448,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_russian_elo_votes","value":1418,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_russian_elo_interval","value":14.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_russian_elo","value":1208.635200541712,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_russian_elo_votes","value":2576,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_russian_elo_interval","value":11.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_russian_elo","value":1173.8510681192497,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_russian_elo_votes","value":1350,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_russian_elo_interval","value":15.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_russian_elo","value":1158.3080863212604,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_russian_elo_votes","value":6589,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_russian_elo_interval","value":8.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_russian_elo","value":948.8884654845963,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_russian_elo_votes","value":933,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_russian_elo_interval","value":22.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_russian_elo","value":941.1593694048725,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_russian_elo_votes","value":953,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_russian_elo_interval","value":22.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_polish_elo","value":1524.3408604019037,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_polish_elo_votes","value":224,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_polish_elo_interval","value":38.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_polish_elo","value":1519.8905437821131,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_polish_elo_votes","value":507,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_polish_elo_interval","value":25.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_polish_elo","value":1516.5371218854748,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_polish_elo_votes","value":799,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_polish_elo_interval","value":21.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_polish_elo","value":1501.62765914064,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_polish_elo_votes","value":426,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_polish_elo_interval","value":28.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_polish_elo","value":1498.490349383088,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_polish_elo_votes","value":550,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_polish_elo_interval","value":25.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_polish_elo","value":1496.652818749466,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_polish_elo_votes","value":2442,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_polish_elo_interval","value":12.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_polish_elo","value":1496.6055423801254,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_polish_elo_votes","value":1535,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_polish_elo_interval","value":15.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_polish_elo","value":1495.4431016614994,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_polish_elo_votes","value":649,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_polish_elo_interval","value":23.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_polish_elo","value":1493.4027063824565,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_polish_elo_votes","value":623,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_polish_elo_interval","value":23.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_polish_elo","value":1489.299240014826,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_polish_elo_votes","value":1122,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_polish_elo_interval","value":17.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_polish_elo","value":1483.0740978367603,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_polish_elo_votes","value":253,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_polish_elo_interval","value":37.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_polish_elo","value":1478.8442779744664,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_polish_elo_votes","value":6495,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_polish_elo_interval","value":8.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_polish_elo","value":1474.758896495835,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_polish_elo_votes","value":532,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_polish_elo_interval","value":25.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_polish_elo","value":1472.37878549972,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_polish_elo_votes","value":408,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_polish_elo_interval","value":27.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_polish_elo","value":1472.0607603338808,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_polish_elo_votes","value":1318,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_polish_elo_interval","value":16.6,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_polish_elo","value":1469.696513686231,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_polish_elo_votes","value":174,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_polish_elo_interval","value":42.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_polish_elo","value":1464.4870640160134,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_polish_elo_votes","value":1356,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_polish_elo_interval","value":16.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_polish_elo","value":1464.4118122574669,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_polish_elo_votes","value":1171,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_polish_elo_interval","value":17.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_polish_elo","value":1461.3948993170598,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_polish_elo_votes","value":616,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_polish_elo_interval","value":23.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_polish_elo","value":1461.2145456895064,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_polish_elo_votes","value":1124,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_polish_elo_interval","value":17.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_polish_elo","value":1459.895745274402,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_polish_elo_votes","value":550,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_polish_elo_interval","value":24.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_polish_elo","value":1459.3185340357586,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_polish_elo_votes","value":1090,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_polish_elo_interval","value":17.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_polish_elo","value":1452.6236752246664,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_polish_elo_votes","value":604,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_polish_elo_interval","value":23.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_polish_elo","value":1449.9097858813657,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_polish_elo_votes","value":236,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_polish_elo_interval","value":36.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_polish_elo","value":1449.5723774126045,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_polish_elo_votes","value":807,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_polish_elo_interval","value":20.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_polish_elo","value":1449.4077834025793,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_polish_elo_votes","value":556,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_polish_elo_interval","value":24.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_polish_elo","value":1448.5149413518757,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_polish_elo_votes","value":1665,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_polish_elo_interval","value":14.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_polish_elo","value":1447.475581750355,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_polish_elo_votes","value":1156,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_polish_elo_interval","value":17.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_polish_elo","value":1447.3972570133096,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_polish_elo_votes","value":629,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_polish_elo_interval","value":22.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_polish_elo","value":1446.7415731230703,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_polish_elo_votes","value":1301,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_polish_elo_interval","value":16.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_polish_elo","value":1442.8410480376974,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_polish_elo_votes","value":1267,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_polish_elo_interval","value":16.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_polish_elo","value":1442.2744335175598,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_polish_elo_votes","value":1412,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_polish_elo_interval","value":15.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_polish_elo","value":1441.7431861556406,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_polish_elo_votes","value":364,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_polish_elo_interval","value":30.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_polish_elo","value":1440.2643125061036,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_polish_elo_votes","value":1321,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_polish_elo_interval","value":15.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_polish_elo","value":1438.74134294958,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_polish_elo_votes","value":1891,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_polish_elo_interval","value":13.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_polish_elo","value":1437.931864620321,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_polish_elo_votes","value":3834,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_polish_elo_interval","value":10.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_polish_elo","value":1437.7195104070765,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_polish_elo_votes","value":759,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_polish_elo_interval","value":20.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_polish_elo","value":1436.985639581952,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_polish_elo_votes","value":522,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_polish_elo_interval","value":25.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_polish_elo","value":1435.25004656395,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_polish_elo_votes","value":1027,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_polish_elo_interval","value":18.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_polish_elo","value":1435.1800929676465,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_polish_elo_votes","value":603,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_polish_elo_interval","value":23.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_polish_elo","value":1434.965805413769,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_polish_elo_votes","value":461,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_polish_elo_interval","value":25.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_polish_elo","value":1433.2453213737995,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_polish_elo_votes","value":998,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_polish_elo_interval","value":18.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_polish_elo","value":1432.5209123203922,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_polish_elo_votes","value":628,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_polish_elo_interval","value":23.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_polish_elo","value":1432.1026302554055,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_polish_elo_votes","value":196,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_polish_elo_interval","value":41.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_polish_elo","value":1431.2033933667917,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_polish_elo_votes","value":203,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_polish_elo_interval","value":37.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_polish_elo","value":1431.1765494414349,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_polish_elo_votes","value":1795,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_polish_elo_interval","value":14.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_polish_elo","value":1429.7047584693505,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_polish_elo_votes","value":233,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_polish_elo_interval","value":37.08,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_polish_elo","value":1429.5149799247579,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_polish_elo_votes","value":436,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_polish_elo_interval","value":27.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_polish_elo","value":1428.1987285827076,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_polish_elo_votes","value":1980,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_polish_elo_interval","value":14.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_polish_elo","value":1426.3843848369165,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_polish_elo_votes","value":710,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_polish_elo_interval","value":22.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_polish_elo","value":1426.0605301415567,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_polish_elo_votes","value":459,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_polish_elo_interval","value":27.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_polish_elo","value":1425.8311800300894,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_polish_elo_votes","value":1631,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_polish_elo_interval","value":14.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_polish_elo","value":1423.576427410142,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_polish_elo_votes","value":1112,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_polish_elo_interval","value":17.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_polish_elo","value":1422.4801767353833,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_polish_elo_votes","value":1676,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_polish_elo_interval","value":14.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_polish_elo","value":1420.088339521722,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_polish_elo_votes","value":440,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_polish_elo_interval","value":27.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_polish_elo","value":1419.4324890798644,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_polish_elo_votes","value":2316,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_polish_elo_interval","value":12.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_polish_elo","value":1419.387456236705,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_polish_elo_votes","value":540,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_polish_elo_interval","value":26.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_polish_elo","value":1415.2042700524548,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_polish_elo_votes","value":1193,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_polish_elo_interval","value":17.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_polish_elo","value":1413.078728693893,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_polish_elo_votes","value":6189,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_polish_elo_interval","value":8.27,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_polish_elo","value":1413.0043277580976,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_polish_elo_votes","value":3733,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_polish_elo_interval","value":10.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_polish_elo","value":1412.7920832398022,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_polish_elo_votes","value":945,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_polish_elo_interval","value":18.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_polish_elo","value":1411.3372721979458,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_polish_elo_votes","value":164,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_polish_elo_interval","value":43.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_polish_elo","value":1408.4638009008345,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_polish_elo_votes","value":1340,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_polish_elo_interval","value":16.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_polish_elo","value":1406.6262764172106,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_polish_elo_votes","value":3945,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_polish_elo_interval","value":9.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_polish_elo","value":1405.0339215405193,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_polish_elo_votes","value":229,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_polish_elo_interval","value":38.08,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_polish_elo","value":1404.287331529771,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_polish_elo_votes","value":610,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_polish_elo_interval","value":24.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_polish_elo","value":1399.1404639920142,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_polish_elo_votes","value":604,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_polish_elo_interval","value":23.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_polish_elo","value":1398.0873201834402,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_polish_elo_votes","value":1022,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_polish_elo_interval","value":18.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_polish_elo","value":1397.7741489324421,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_polish_elo_votes","value":1201,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_polish_elo_interval","value":17.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_polish_elo","value":1389.9609321069568,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_polish_elo_votes","value":783,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_polish_elo_interval","value":20.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_polish_elo","value":1389.2923948680232,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_polish_elo_votes","value":1364,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_polish_elo_interval","value":16.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_polish_elo","value":1388.8385295053147,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_polish_elo_votes","value":3051,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_polish_elo_interval","value":11.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_polish_elo","value":1388.387323697879,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_polish_elo_votes","value":1648,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_polish_elo_interval","value":14.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_polish_elo","value":1385.8296004899025,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_polish_elo_votes","value":585,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_polish_elo_interval","value":22.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_polish_elo","value":1378.388362619277,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_polish_elo_votes","value":1563,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_polish_elo_interval","value":15.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_polish_elo","value":1376.2394568357035,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_polish_elo_votes","value":1286,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_polish_elo_interval","value":16.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_polish_elo","value":1374.4754317241143,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_polish_elo_votes","value":537,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_polish_elo_interval","value":24.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_polish_elo","value":1368.4481965816858,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_polish_elo_votes","value":2736,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_polish_elo_interval","value":11.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_polish_elo","value":1367.7222122558196,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_polish_elo_votes","value":1861,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_polish_elo_interval","value":14.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_polish_elo","value":1365.1898187407724,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_polish_elo_votes","value":1129,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_polish_elo_interval","value":18.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_polish_elo","value":1364.726709291141,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_polish_elo_votes","value":166,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_polish_elo_interval","value":56.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_polish_elo","value":1357.7916906974026,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_polish_elo_votes","value":2795,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_polish_elo_interval","value":11.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_polish_elo","value":1353.3442524680936,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_polish_elo_votes","value":1733,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_polish_elo_interval","value":14.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_polish_elo","value":1353.1910627391821,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_polish_elo_votes","value":1541,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_polish_elo_interval","value":15.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_polish_elo","value":1345.5079453613766,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_polish_elo_votes","value":276,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_polish_elo_interval","value":34.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_polish_elo","value":1345.1220359631238,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_polish_elo_votes","value":2830,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_polish_elo_interval","value":11.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_polish_elo","value":1344.9631961754258,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_polish_elo_votes","value":709,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_polish_elo_interval","value":22.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_polish_elo","value":1344.4365594723783,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_polish_elo_votes","value":1619,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_polish_elo_interval","value":15.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_polish_elo","value":1341.8870678048668,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_polish_elo_votes","value":3483,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_polish_elo_interval","value":10.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_polish_elo","value":1333.743114963309,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_polish_elo_votes","value":929,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_polish_elo_interval","value":19.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_polish_elo","value":1329.414627480981,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_polish_elo_votes","value":3526,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_polish_elo_interval","value":10.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_polish_elo","value":1327.1206650049642,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_polish_elo_votes","value":421,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_polish_elo_interval","value":29.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_polish_elo","value":1325.9999748714552,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_polish_elo_votes","value":2669,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_polish_elo_interval","value":12.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_polish_elo","value":1324.2664349265779,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_polish_elo_votes","value":3071,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_polish_elo_interval","value":11.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_polish_elo","value":1313.7458390282954,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_polish_elo_votes","value":571,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_polish_elo_interval","value":24.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_polish_elo","value":1311.3361432095505,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_polish_elo_votes","value":279,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_polish_elo_interval","value":35.89,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_polish_elo","value":1310.4243836113544,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_polish_elo_votes","value":567,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_polish_elo_interval","value":26.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_polish_elo","value":1302.375399662145,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_polish_elo_votes","value":281,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_polish_elo_interval","value":34.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_polish_elo","value":1302.1237062480373,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_polish_elo_votes","value":306,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_polish_elo_interval","value":34.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_polish_elo","value":1299.3152263400466,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_polish_elo_votes","value":2004,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_polish_elo_interval","value":13.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_polish_elo","value":1294.2597941644317,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_polish_elo_votes","value":2638,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_polish_elo_interval","value":12.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_polish_elo","value":1290.8306395918075,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_polish_elo_votes","value":318,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_polish_elo_interval","value":32.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_polish_elo","value":1277.2721970250602,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_polish_elo_votes","value":58,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_polish_elo_interval","value":73.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_polish_elo","value":1275.584588153973,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_polish_elo_votes","value":2675,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_polish_elo_interval","value":12.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_polish_elo","value":1264.8800636499464,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_polish_elo_votes","value":2468,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_polish_elo_interval","value":12.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_polish_elo","value":1259.1654289243656,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_polish_elo_votes","value":1454,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_polish_elo_interval","value":16.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_polish_elo","value":1252.2370447496992,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_polish_elo_votes","value":808,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_polish_elo_interval","value":22.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_polish_elo","value":1244.0084449293154,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_polish_elo_votes","value":65,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_polish_elo_interval","value":65.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_polish_elo","value":1241.6268132347718,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_polish_elo_votes","value":2795,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_polish_elo_interval","value":12.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_multi_turn_elo","value":1555.9585443122837,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":680,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":23.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_multi_turn_elo","value":1517.6256208461427,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":431,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":28.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_multi_turn_elo","value":1512.1611556567877,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":13816,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":6.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_multi_turn_elo","value":1505.589740236232,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":11424,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":6.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_multi_turn_elo","value":1505.3792218304377,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":6819,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":7.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_multi_turn_elo","value":1502.3110137354095,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":1206,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":17.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_multi_turn_elo","value":1501.9532878626399,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":5601,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":8.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_multi_turn_elo","value":1501.6504363452525,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":1088,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":18.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_multi_turn_elo","value":1498.6541259678306,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":4900,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":9.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_multi_turn_elo","value":1493.2792303871113,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":1922,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":13.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_multi_turn_elo","value":1487.6186300993177,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":5013,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":8.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_multi_turn_elo","value":1487.1867526925635,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":4222,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":9.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_multi_turn_elo","value":1486.5979274733486,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":4139,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":9.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_multi_turn_elo","value":1486.4567651185203,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":21640,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":5.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_multi_turn_elo","value":1486.198410516713,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":2622,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":11.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_multi_turn_elo","value":1483.242952669894,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":6502,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":8.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_multi_turn_elo","value":1482.1124137349136,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":11988,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":6.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_multi_turn_elo","value":1480.9369696022773,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":8090,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":7.36,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_multi_turn_elo","value":1480.7732296020595,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":5798,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":8.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_multi_turn_elo","value":1477.0246538761266,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":12792,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":6.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_multi_turn_elo","value":1475.8500980567537,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":11832,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":6.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_multi_turn_elo","value":1475.2937962888527,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":11189,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":6.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_multi_turn_elo","value":1472.4066630356378,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":9941,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":6.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_multi_turn_elo","value":1468.857164435689,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":5012,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":8.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_multi_turn_elo","value":1467.3805699905558,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":10357,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":6.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_multi_turn_elo","value":1466.1801065522916,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":12968,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":5.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_multi_turn_elo","value":1464.9345948707908,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":14479,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":5.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_multi_turn_elo","value":1463.799852720345,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":12693,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":6.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_multi_turn_elo","value":1462.9146484588036,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":587,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":23.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_multi_turn_elo","value":1462.877002220319,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":1008,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":18.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_multi_turn_elo","value":1459.8891741201226,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":6597,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":8.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_multi_turn_elo","value":1459.7545447466223,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":7009,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":7.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_multi_turn_elo","value":1456.0201359310447,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":4688,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":8.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_multi_turn_elo","value":1455.9984671800223,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":6632,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":8.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_multi_turn_elo","value":1453.1699379976853,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":6941,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":7.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_multi_turn_elo","value":1452.8509637026536,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":8377,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":7.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_multi_turn_elo","value":1452.6303206395269,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":21195,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":4.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_multi_turn_elo","value":1452.154237808559,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":1124,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":17.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_multi_turn_elo","value":1451.7510943894335,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":6941,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":7.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_multi_turn_elo","value":1449.5237825405984,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":7244,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":7.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_multi_turn_elo","value":1448.8887792471912,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":1630,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":14.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_multi_turn_elo","value":1448.4786349791577,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":9346,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":7.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_multi_turn_elo","value":1446.2285639435177,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":15114,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":5.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_multi_turn_elo","value":1445.9328361828968,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":1931,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":13.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_multi_turn_elo","value":1445.3533452893607,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":8382,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":7.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_multi_turn_elo","value":1443.9971356401134,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":5866,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":8.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_multi_turn_elo","value":1443.1485863574355,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":13115,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":5.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_multi_turn_elo","value":1442.9712048987285,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":11126,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":6.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_multi_turn_elo","value":1441.5648239867453,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":3711,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":10.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_multi_turn_elo","value":1441.3295135868823,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":1143,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":16.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_multi_turn_elo","value":1441.065722638961,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":983,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":18.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_multi_turn_elo","value":1437.9065976759334,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":8445,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":7.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_multi_turn_elo","value":1437.441831966532,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":6369,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":8.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_multi_turn_elo","value":1437.287433381899,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":1069,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":18.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_multi_turn_elo","value":1434.6820485012024,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":1965,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":13.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_multi_turn_elo","value":1433.817215061123,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":6622,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":8.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_multi_turn_elo","value":1432.0957626434404,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":17054,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_multi_turn_elo","value":1431.6605498315987,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":1732,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":14.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_multi_turn_elo","value":1429.020483506796,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":11877,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":6.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_multi_turn_elo","value":1427.984161862303,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":1929,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":14.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_multi_turn_elo","value":1426.96524536922,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":5615,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":8.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_multi_turn_elo","value":1426.9508946773265,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":8341,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":7.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_multi_turn_elo","value":1426.0776970755844,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":5682,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":8.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_multi_turn_elo","value":1424.1586500883752,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":1917,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":13.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_multi_turn_elo","value":1423.9305418066801,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":4363,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":9.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_multi_turn_elo","value":1421.4938882532379,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":1992,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":12.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_multi_turn_elo","value":1419.310262461108,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":9245,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":6.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_multi_turn_elo","value":1417.089841884605,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":11592,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":6.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_multi_turn_elo","value":1416.5141494524157,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":5201,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":8.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_multi_turn_elo","value":1415.796791170432,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":4015,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":9.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_multi_turn_elo","value":1414.960804224143,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":3706,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":9.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_multi_turn_elo","value":1414.2151567053604,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":4945,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":9.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_multi_turn_elo","value":1411.968086963761,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":14532,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":5.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_multi_turn_elo","value":1410.031559048549,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":4893,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":8.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_multi_turn_elo","value":1409.4225220842598,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":25888,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":4.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_multi_turn_elo","value":1407.9041430240904,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":21709,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":4.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_multi_turn_elo","value":1406.4410116165827,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":1357,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":15.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_multi_turn_elo","value":1405.6202204339618,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":12856,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":6.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_multi_turn_elo","value":1404.6547924354616,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":10377,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":6.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_multi_turn_elo","value":1404.6299442817142,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":9655,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":6.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_multi_turn_elo","value":1404.3715587225672,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":2848,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":10.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_multi_turn_elo","value":1397.7124534625875,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":8733,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":6.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_multi_turn_elo","value":1392.4327740893762,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":10982,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":6.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_multi_turn_elo","value":1390.9507181442157,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":1721,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":14.6,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_multi_turn_elo","value":1390.172853358794,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":5481,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":8.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_multi_turn_elo","value":1388.526123114832,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":7685,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":7.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_multi_turn_elo","value":1387.918824421401,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":658,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":22.6,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_multi_turn_elo","value":1382.7188683632294,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":3130,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":11.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_multi_turn_elo","value":1382.1948891922345,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":11780,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":6.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_multi_turn_elo","value":1378.3521290688213,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":3932,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":9.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_multi_turn_elo","value":1371.067362544461,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":4994,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":8.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_multi_turn_elo","value":1369.212155276463,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":1365,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":15.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_multi_turn_elo","value":1365.4322670826305,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":4252,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":9.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_multi_turn_elo","value":1363.5449001962327,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":7726,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":7.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_multi_turn_elo","value":1362.874976499988,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":4396,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":9.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_multi_turn_elo","value":1361.3622754395888,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":1093,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":17.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_multi_turn_elo","value":1358.799647523242,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":488,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":25.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_multi_turn_elo","value":1356.8104590958906,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":551,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":24.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_multi_turn_elo","value":1354.751371709939,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":4399,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":9.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_multi_turn_elo","value":1353.9923872620936,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":7003,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":7.6,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_multi_turn_elo","value":1349.939729191827,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":7746,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":7.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_multi_turn_elo","value":1346.4764974703955,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":2217,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":12.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_multi_turn_elo","value":1344.594873344149,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":6728,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":7.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_multi_turn_elo","value":1341.7556643244068,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":2139,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":12.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_multi_turn_elo","value":1339.7643576727207,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":4883,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":8.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_multi_turn_elo","value":1338.4954460165534,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":9289,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":6.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_multi_turn_elo","value":1338.191448519525,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":2091,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":13.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_multi_turn_elo","value":1334.9776430622005,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":5438,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":8.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_multi_turn_elo","value":1333.750201163516,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":471,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":25.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_multi_turn_elo","value":1333.1534742940692,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":849,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":20.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_multi_turn_elo","value":1330.8260661195038,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":590,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":22.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_multi_turn_elo","value":1320.4500731831317,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":2535,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":11.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_multi_turn_elo","value":1320.0931906454218,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":5608,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":8.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_multi_turn_elo","value":1312.8965315130401,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":9301,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":6.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_multi_turn_elo","value":1311.359776383813,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":1418,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":15.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_multi_turn_elo","value":1307.0262311610543,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":4397,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":9.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_multi_turn_elo","value":1301.623948225134,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":20434,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":6.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_multi_turn_elo","value":1301.3613072347664,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":524,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":28.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_multi_turn_elo","value":1289.381770686749,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":6681,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":7.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_multi_turn_elo","value":1285.0612183001929,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":12279,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":6.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_multi_turn_elo","value":1280.2790814244413,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":5230,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":8.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_multi_turn_elo","value":1279.4865224207153,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":9059,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":6.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_multi_turn_elo","value":1278.807819796419,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":8201,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":7.89,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_multi_turn_elo","value":1276.6680618591051,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":1000,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":18.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_multi_turn_elo","value":1271.7688216422443,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":7250,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":7.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_multi_turn_elo","value":1270.3755407672604,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":5411,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":8.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_multi_turn_elo","value":1268.1947845709642,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":1777,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":14.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_multi_turn_elo","value":1257.2798340243255,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":8296,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":7.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_multi_turn_elo","value":1256.125100649504,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":10405,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":7.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_multi_turn_elo","value":1255.200425523811,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":565,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":23.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_multi_turn_elo","value":1223.6948771086234,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":13588,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":6.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_multi_turn_elo","value":1222.3009832829482,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":1024,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":17.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_multi_turn_elo","value":1216.6064926513639,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":2151,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":12.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_multi_turn_elo","value":1212.7022943061854,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":1826,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":13.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_multi_turn_elo","value":1205.890843807954,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":3517,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":10.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_multi_turn_elo","value":1171.9702413698035,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":8930,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":7.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_multi_turn_elo","value":1163.0168776433088,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":1851,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":13.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_multi_turn_elo","value":1105.0802496941876,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":1299,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":16.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_multi_turn_elo","value":1029.8302225017655,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_multi_turn_elo_votes","value":1236,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_multi_turn_elo_interval","value":18.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_longer_query_elo","value":1546.404856237763,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_longer_query_elo_votes","value":2064,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_longer_query_elo_interval","value":13.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_longer_query_elo","value":1530.9623379449245,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_longer_query_elo_votes","value":3519,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_longer_query_elo_interval","value":10.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_longer_query_elo","value":1522.8678745529573,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_longer_query_elo_votes","value":6028,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_longer_query_elo_interval","value":8.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_longer_query_elo","value":1518.092557089324,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_longer_query_elo_votes","value":34498,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_longer_query_elo_interval","value":4.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_longer_query_elo","value":1516.3362648996247,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_longer_query_elo_votes","value":15315,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_longer_query_elo_interval","value":6.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_longer_query_elo","value":1509.7346384436796,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_longer_query_elo_votes","value":19543,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_longer_query_elo_interval","value":5.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_longer_query_elo","value":1507.0979299023222,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_longer_query_elo_votes","value":17232,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_longer_query_elo_interval","value":6.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_longer_query_elo","value":1505.5236827192016,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_longer_query_elo_votes","value":30078,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_longer_query_elo_interval","value":5.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_longer_query_elo","value":1500.090671534096,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_longer_query_elo_votes","value":1655,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_longer_query_elo_interval","value":14.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_longer_query_elo","value":1493.728288501509,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_longer_query_elo_votes","value":2882,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_longer_query_elo_interval","value":11.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_longer_query_elo","value":1492.6786240144897,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_longer_query_elo_votes","value":14255,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_longer_query_elo_interval","value":6.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_longer_query_elo","value":1492.347718826823,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_longer_query_elo_votes","value":12678,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_longer_query_elo_interval","value":6.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_longer_query_elo","value":1489.836429453935,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_longer_query_elo_votes","value":1437,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_longer_query_elo_interval","value":15.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_longer_query_elo","value":1488.3625456963885,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_longer_query_elo_votes","value":12332,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_longer_query_elo_interval","value":6.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_longer_query_elo","value":1487.6234080734262,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_longer_query_elo_votes","value":7962,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_longer_query_elo_interval","value":7.6,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_longer_query_elo","value":1484.2755879213225,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_longer_query_elo_votes","value":32045,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_longer_query_elo_interval","value":4.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_longer_query_elo","value":1483.5126905822965,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_longer_query_elo_votes","value":30215,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_longer_query_elo_interval","value":5.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_longer_query_elo","value":1482.6741147856615,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_longer_query_elo_votes","value":56414,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_longer_query_elo_interval","value":4.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_longer_query_elo","value":1482.561719758969,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_longer_query_elo_votes","value":22808,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_longer_query_elo_interval","value":5.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_longer_query_elo","value":1482.2908584723132,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_longer_query_elo_votes","value":14580,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_longer_query_elo_interval","value":6.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_longer_query_elo","value":1482.0112023016422,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_longer_query_elo_votes","value":33640,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_longer_query_elo_interval","value":4.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_longer_query_elo","value":1480.8149815760335,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_longer_query_elo_votes","value":18670,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_longer_query_elo_interval","value":5.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_longer_query_elo","value":1479.0916184666137,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_longer_query_elo_votes","value":24254,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_longer_query_elo_interval","value":4.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_longer_query_elo","value":1478.958026231338,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_longer_query_elo_votes","value":31070,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_longer_query_elo_interval","value":4.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_longer_query_elo","value":1476.1344709768991,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_longer_query_elo_votes","value":3627,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_longer_query_elo_interval","value":10.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_longer_query_elo","value":1475.3243714824998,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_longer_query_elo_votes","value":26489,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_longer_query_elo_interval","value":4.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_longer_query_elo","value":1474.4982318042453,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_longer_query_elo_votes","value":17161,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_longer_query_elo_interval","value":5.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_longer_query_elo","value":1473.1359139019323,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_longer_query_elo_votes","value":28438,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_longer_query_elo_interval","value":5.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_longer_query_elo","value":1468.2936504952777,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_longer_query_elo_votes","value":16968,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_longer_query_elo_interval","value":6.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_longer_query_elo","value":1466.9012905596142,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_longer_query_elo_votes","value":28385,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_longer_query_elo_interval","value":4.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_longer_query_elo","value":1462.5898125110887,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_longer_query_elo_votes","value":19283,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_longer_query_elo_interval","value":5.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_longer_query_elo","value":1462.581493318886,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_longer_query_elo_votes","value":22955,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_longer_query_elo_interval","value":5.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_longer_query_elo","value":1461.9923775446841,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_longer_query_elo_votes","value":19809,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_longer_query_elo_interval","value":5.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_longer_query_elo","value":1459.1207796322628,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_longer_query_elo_votes","value":4483,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_longer_query_elo_interval","value":9.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_longer_query_elo","value":1457.4047844376746,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_longer_query_elo_votes","value":25932,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_longer_query_elo_interval","value":5.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_longer_query_elo","value":1454.8856041985978,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_longer_query_elo_votes","value":13401,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_longer_query_elo_interval","value":6.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_longer_query_elo","value":1454.5115945407965,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_longer_query_elo_votes","value":19564,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_longer_query_elo_interval","value":5.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_longer_query_elo","value":1452.8298821314797,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_longer_query_elo_votes","value":20120,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_longer_query_elo_interval","value":5.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_longer_query_elo","value":1449.2533152328936,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_longer_query_elo_votes","value":10316,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_longer_query_elo_interval","value":6.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_longer_query_elo","value":1449.142972967146,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_longer_query_elo_votes","value":34031,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_longer_query_elo_interval","value":3.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_longer_query_elo","value":1448.1157238822934,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_longer_query_elo_votes","value":3019,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_longer_query_elo_interval","value":11.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_longer_query_elo","value":1447.7232181901436,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_longer_query_elo_votes","value":10937,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_longer_query_elo_interval","value":6.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_longer_query_elo","value":1446.1842029242052,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_longer_query_elo_votes","value":1801,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_longer_query_elo_interval","value":13.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_longer_query_elo","value":1445.9364674065905,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_longer_query_elo_votes","value":28906,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_longer_query_elo_interval","value":5.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_longer_query_elo","value":1445.4591595263291,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_longer_query_elo_votes","value":11126,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_longer_query_elo_interval","value":6.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_longer_query_elo","value":1444.6588093050145,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_longer_query_elo_votes","value":21302,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_longer_query_elo_interval","value":5.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_longer_query_elo","value":1444.1798953467733,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_longer_query_elo_votes","value":18482,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_longer_query_elo_interval","value":5.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_longer_query_elo","value":1441.6565921727827,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_longer_query_elo_votes","value":41250,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_longer_query_elo_interval","value":4.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_longer_query_elo","value":1440.6707361322283,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_longer_query_elo_votes","value":5528,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_longer_query_elo_interval","value":8.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_longer_query_elo","value":1439.0827178371555,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_longer_query_elo_votes","value":4899,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_longer_query_elo_interval","value":8.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_longer_query_elo","value":1439.0541244466347,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_longer_query_elo_votes","value":21175,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_longer_query_elo_interval","value":5.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_longer_query_elo","value":1436.5164040239579,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_longer_query_elo_votes","value":19367,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_longer_query_elo_interval","value":5.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_longer_query_elo","value":1434.5664720603518,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_longer_query_elo_votes","value":17112,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_longer_query_elo_interval","value":5.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_longer_query_elo","value":1433.9914989881718,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_longer_query_elo_votes","value":23356,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_longer_query_elo_interval","value":5.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_longer_query_elo","value":1433.5802630775556,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_longer_query_elo_votes","value":19084,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_longer_query_elo_interval","value":5.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_longer_query_elo","value":1432.6071290133439,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_longer_query_elo_votes","value":3267,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_longer_query_elo_interval","value":10.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_longer_query_elo","value":1428.0178745529154,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_longer_query_elo_votes","value":13732,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_longer_query_elo_interval","value":5.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_longer_query_elo","value":1427.2727503933725,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_longer_query_elo_votes","value":1715,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_longer_query_elo_interval","value":13.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_longer_query_elo","value":1426.949898957015,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_longer_query_elo_votes","value":56594,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_longer_query_elo_interval","value":3.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_longer_query_elo","value":1426.7557720936964,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_longer_query_elo_votes","value":3141,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_longer_query_elo_interval","value":11.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_longer_query_elo","value":1425.9906380085242,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_longer_query_elo_votes","value":27123,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_longer_query_elo_interval","value":4.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_longer_query_elo","value":1422.3988342113662,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_longer_query_elo_votes","value":9145,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_longer_query_elo_interval","value":6.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_longer_query_elo","value":1419.897286100473,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_longer_query_elo_votes","value":2250,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_longer_query_elo_interval","value":12.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_longer_query_elo","value":1418.887664546007,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_longer_query_elo_votes","value":33331,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_longer_query_elo_interval","value":3.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_longer_query_elo","value":1418.7627333339867,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_longer_query_elo_votes","value":36152,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_longer_query_elo_interval","value":4.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_longer_query_elo","value":1417.6200658474818,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_longer_query_elo_votes","value":3064,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_longer_query_elo_interval","value":10.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_longer_query_elo","value":1416.0822435986977,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_longer_query_elo_votes","value":4785,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_longer_query_elo_interval","value":9.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_longer_query_elo","value":1415.5839558520968,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_longer_query_elo_votes","value":5095,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_longer_query_elo_interval","value":9.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_longer_query_elo","value":1412.8913060571354,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_longer_query_elo_votes","value":11050,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_longer_query_elo_interval","value":6.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_longer_query_elo","value":1412.658487871035,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_longer_query_elo_votes","value":34073,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_longer_query_elo_interval","value":4.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_longer_query_elo","value":1412.4497974292767,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_longer_query_elo_votes","value":5085,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_longer_query_elo_interval","value":8.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_longer_query_elo","value":1410.1909912947406,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_longer_query_elo_votes","value":11732,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_longer_query_elo_interval","value":6.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_longer_query_elo","value":1407.3060968982284,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_longer_query_elo_votes","value":27795,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_longer_query_elo_interval","value":5.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_longer_query_elo","value":1402.5319828354206,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_longer_query_elo_votes","value":5396,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_longer_query_elo_interval","value":8.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_longer_query_elo","value":1401.7307073995378,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_longer_query_elo_votes","value":22834,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_longer_query_elo_interval","value":5.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_longer_query_elo","value":1400.668769581767,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_longer_query_elo_votes","value":15204,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_longer_query_elo_interval","value":6.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_longer_query_elo","value":1399.0959375812463,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_longer_query_elo_votes","value":1641,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_longer_query_elo_interval","value":14.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_longer_query_elo","value":1398.6634807255527,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_longer_query_elo_votes","value":6840,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_longer_query_elo_interval","value":7.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_longer_query_elo","value":1395.5675202167715,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_longer_query_elo_votes","value":842,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_longer_query_elo_interval","value":19.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_longer_query_elo","value":1394.37713966276,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_longer_query_elo_votes","value":27228,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_longer_query_elo_interval","value":5.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_longer_query_elo","value":1392.7125137915825,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_longer_query_elo_votes","value":33219,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_longer_query_elo_interval","value":4.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_longer_query_elo","value":1391.7434722942874,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_longer_query_elo_votes","value":25685,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_longer_query_elo_interval","value":5.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_longer_query_elo","value":1391.2697750924858,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_longer_query_elo_votes","value":3129,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_longer_query_elo_interval","value":10.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_longer_query_elo","value":1389.568021345269,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_longer_query_elo_votes","value":11908,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_longer_query_elo_interval","value":6.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_longer_query_elo","value":1384.716529482114,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_longer_query_elo_votes","value":9965,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_longer_query_elo_interval","value":6.36,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_longer_query_elo","value":1380.2167840435714,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_longer_query_elo_votes","value":9833,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_longer_query_elo_interval","value":7.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_longer_query_elo","value":1378.3551030826784,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_longer_query_elo_votes","value":4942,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_longer_query_elo_interval","value":8.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_longer_query_elo","value":1378.1304187038581,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_longer_query_elo_votes","value":4937,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_longer_query_elo_interval","value":8.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_longer_query_elo","value":1377.5310716145445,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_longer_query_elo_votes","value":3571,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_longer_query_elo_interval","value":9.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_longer_query_elo","value":1371.6080708245458,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_longer_query_elo_votes","value":11540,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_longer_query_elo_interval","value":6.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_longer_query_elo","value":1366.1104016759882,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_longer_query_elo_votes","value":6773,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_longer_query_elo_interval","value":7.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_longer_query_elo","value":1365.5937094970402,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_longer_query_elo_votes","value":16279,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_longer_query_elo_interval","value":5.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_longer_query_elo","value":1365.515526820685,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_longer_query_elo_votes","value":27722,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_longer_query_elo_interval","value":5.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_longer_query_elo","value":1361.9934402129836,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_longer_query_elo_votes","value":2272,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_longer_query_elo_interval","value":11.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_longer_query_elo","value":1357.2651352401294,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_longer_query_elo_votes","value":706,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_longer_query_elo_interval","value":21.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_longer_query_elo","value":1354.8449875358508,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_longer_query_elo_votes","value":5902,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_longer_query_elo_interval","value":8.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_longer_query_elo","value":1352.8413219378424,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_longer_query_elo_votes","value":2881,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_longer_query_elo_interval","value":10.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_longer_query_elo","value":1352.0298576261237,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_longer_query_elo_votes","value":8531,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_longer_query_elo_interval","value":6.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_longer_query_elo","value":1344.5163113011256,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_longer_query_elo_votes","value":3380,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_longer_query_elo_interval","value":10.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_longer_query_elo","value":1343.8210237439314,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_longer_query_elo_votes","value":7071,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_longer_query_elo_interval","value":7.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_longer_query_elo","value":1342.7809002657316,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_longer_query_elo_votes","value":2160,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_longer_query_elo_interval","value":12.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_longer_query_elo","value":1335.4844150342556,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_longer_query_elo_votes","value":3072,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_longer_query_elo_interval","value":10.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_longer_query_elo","value":1334.119984147516,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_longer_query_elo_votes","value":10709,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_longer_query_elo_interval","value":6.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_longer_query_elo","value":1333.1503553815453,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_longer_query_elo_votes","value":6675,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_longer_query_elo_interval","value":7.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_longer_query_elo","value":1330.9536944357326,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_longer_query_elo_votes","value":1657,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_longer_query_elo_interval","value":14.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_longer_query_elo","value":1329.5368432245873,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_longer_query_elo_votes","value":919,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_longer_query_elo_interval","value":19.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_longer_query_elo","value":1327.1900144583906,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_longer_query_elo_votes","value":9263,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_longer_query_elo_interval","value":6.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_longer_query_elo","value":1327.1365333340057,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_longer_query_elo_votes","value":504,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_longer_query_elo_interval","value":24.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_longer_query_elo","value":1326.2292352260217,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_longer_query_elo_votes","value":6984,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_longer_query_elo_interval","value":7.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_longer_query_elo","value":1324.8686483681963,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_longer_query_elo_votes","value":1362,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_longer_query_elo_interval","value":17.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_longer_query_elo","value":1319.1740270623002,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_longer_query_elo_votes","value":6565,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_longer_query_elo_interval","value":7.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_longer_query_elo","value":1318.3028790800042,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_longer_query_elo_votes","value":13091,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_longer_query_elo_interval","value":6.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_longer_query_elo","value":1316.7349747326866,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_longer_query_elo_votes","value":371,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_longer_query_elo_interval","value":27.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_longer_query_elo","value":1314.5661105305978,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_longer_query_elo_votes","value":8621,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_longer_query_elo_interval","value":6.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_longer_query_elo","value":1312.3272414833157,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_longer_query_elo_votes","value":1628,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_longer_query_elo_interval","value":14.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_longer_query_elo","value":1311.8226313804732,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_longer_query_elo_votes","value":4496,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_longer_query_elo_interval","value":8.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_longer_query_elo","value":1304.6507764713708,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_longer_query_elo_votes","value":1063,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_longer_query_elo_interval","value":17.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_longer_query_elo","value":1298.4214932620503,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_longer_query_elo_votes","value":6343,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_longer_query_elo_interval","value":7.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_longer_query_elo","value":1288.6967344924456,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_longer_query_elo_votes","value":8989,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_longer_query_elo_interval","value":7.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_longer_query_elo","value":1288.3281089158656,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_longer_query_elo_votes","value":14922,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_longer_query_elo_interval","value":6.89,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_longer_query_elo","value":1283.2026974642358,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_longer_query_elo_votes","value":6160,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_longer_query_elo_interval","value":8.36,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_longer_query_elo","value":1282.5030445406117,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_longer_query_elo_votes","value":730,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_longer_query_elo_interval","value":19.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_longer_query_elo","value":1281.400185707643,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_longer_query_elo_votes","value":6008,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_longer_query_elo_interval","value":8.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_longer_query_elo","value":1279.6689006090578,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_longer_query_elo_votes","value":7075,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_longer_query_elo_interval","value":7.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_longer_query_elo","value":1273.2986143212988,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_longer_query_elo_votes","value":444,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_longer_query_elo_interval","value":26.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_longer_query_elo","value":1264.8469362716978,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_longer_query_elo_votes","value":5809,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_longer_query_elo_interval","value":8.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_longer_query_elo","value":1257.2313154357173,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_longer_query_elo_votes","value":5885,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_longer_query_elo_interval","value":8.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_longer_query_elo","value":1255.349675685645,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_longer_query_elo_votes","value":8330,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_longer_query_elo_interval","value":6.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_longer_query_elo","value":1250.5191593889303,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_longer_query_elo_votes","value":804,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_longer_query_elo_interval","value":18.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_longer_query_elo","value":1250.3809786119136,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_longer_query_elo_votes","value":2104,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_longer_query_elo_interval","value":13.27,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_longer_query_elo","value":1245.6376580625192,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_longer_query_elo_votes","value":1767,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_longer_query_elo_interval","value":13.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_longer_query_elo","value":1240.672318683868,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_longer_query_elo_votes","value":7622,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_longer_query_elo_interval","value":7.6,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_longer_query_elo","value":1230.2941947612046,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_longer_query_elo_votes","value":9918,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_longer_query_elo_interval","value":6.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_longer_query_elo","value":1230.0825473534617,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_longer_query_elo_votes","value":1369,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_longer_query_elo_interval","value":15.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_longer_query_elo","value":1217.0447638767741,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_longer_query_elo_votes","value":2896,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_longer_query_elo_interval","value":10.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_longer_query_elo","value":1197.3857115466533,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_longer_query_elo_votes","value":1421,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_longer_query_elo_interval","value":14.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_longer_query_elo","value":1181.3202369278843,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_longer_query_elo_votes","value":6736,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_longer_query_elo_interval","value":8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_longer_query_elo","value":1100.1971514767704,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_longer_query_elo_votes","value":1046,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_longer_query_elo_interval","value":17.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_longer_query_elo","value":1049.5279982458,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_longer_query_elo_votes","value":1057,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_longer_query_elo_interval","value":18.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_expert_elo","value":1554.6267410416835,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_expert_elo_votes","value":7467,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_expert_elo_interval","value":8.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_expert_elo","value":1550.76567922705,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_expert_elo_votes","value":510,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_expert_elo_interval","value":25.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_expert_elo","value":1549.6300473209203,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_expert_elo_votes","value":907,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_expert_elo_interval","value":19.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_expert_elo","value":1544.8866980000098,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_expert_elo_votes","value":7403,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_expert_elo_interval","value":7.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_expert_elo","value":1540.708000984586,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_expert_elo_votes","value":464,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_expert_elo_interval","value":26.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_expert_elo","value":1539.6542512338274,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_expert_elo_votes","value":1264,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_expert_elo_interval","value":17.08,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_expert_elo","value":1534.8611458126911,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_expert_elo_votes","value":4679,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_expert_elo_interval","value":9.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_expert_elo","value":1532.223441349873,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_expert_elo_votes","value":700,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_expert_elo_interval","value":22.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_expert_elo","value":1524.6823284498957,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_expert_elo_votes","value":4424,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_expert_elo_interval","value":9.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_expert_elo","value":1520.6824191764617,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_expert_elo_votes","value":7101,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_expert_elo_interval","value":7.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_expert_elo","value":1520.3345546229784,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_expert_elo_votes","value":3003,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_expert_elo_interval","value":11.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_expert_elo","value":1516.705926953678,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_expert_elo_votes","value":1934,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_expert_elo_interval","value":13.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_expert_elo","value":1516.233310156213,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_expert_elo_votes","value":4517,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_expert_elo_interval","value":9.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_expert_elo","value":1510.284693172837,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_expert_elo_votes","value":3417,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_expert_elo_interval","value":10.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_expert_elo","value":1509.8446868567933,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_expert_elo_votes","value":3121,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_expert_elo_interval","value":11.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_expert_elo","value":1507.7623853569653,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_expert_elo_votes","value":7408,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_expert_elo_interval","value":7.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_expert_elo","value":1507.1022700216322,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_expert_elo_votes","value":3086,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_expert_elo_interval","value":10.89,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_expert_elo","value":1506.4819867962676,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_expert_elo_votes","value":6359,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_expert_elo_interval","value":8.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_expert_elo","value":1502.523975145121,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_expert_elo_votes","value":7067,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_expert_elo_interval","value":7.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_expert_elo","value":1501.5616193437265,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_expert_elo_votes","value":7439,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_expert_elo_interval","value":7.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_expert_elo","value":1500.1617934839276,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_expert_elo_votes","value":7384,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_expert_elo_interval","value":7.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_expert_elo","value":1495.9600450809548,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_expert_elo_votes","value":351,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_expert_elo_interval","value":30.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_expert_elo","value":1494.9653761449608,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_expert_elo_votes","value":5582,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_expert_elo_interval","value":8.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_expert_elo","value":1494.7053600708523,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_expert_elo_votes","value":1110,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_expert_elo_interval","value":17.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_expert_elo","value":1494.6168054314785,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_expert_elo_votes","value":5032,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_expert_elo_interval","value":8.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_expert_elo","value":1490.7395865011242,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_expert_elo_votes","value":3852,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_expert_elo_interval","value":9.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_expert_elo","value":1490.510834740038,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_expert_elo_votes","value":5522,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_expert_elo_interval","value":8.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_expert_elo","value":1489.0469474516785,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_expert_elo_votes","value":4228,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_expert_elo_interval","value":9.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_expert_elo","value":1487.2521891762171,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_expert_elo_votes","value":5688,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_expert_elo_interval","value":8.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_expert_elo","value":1483.4251462637642,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_expert_elo_votes","value":13288,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_expert_elo_interval","value":6.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_expert_elo","value":1480.5954377698044,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_expert_elo_votes","value":2583,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_expert_elo_interval","value":11.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_expert_elo","value":1478.1978889861202,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_expert_elo_votes","value":4671,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_expert_elo_interval","value":9.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_expert_elo","value":1477.761888796319,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_expert_elo_votes","value":5023,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_expert_elo_interval","value":8.89,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_expert_elo","value":1476.9411825433288,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_expert_elo_votes","value":6716,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_expert_elo_interval","value":7.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_expert_elo","value":1473.6553372468268,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_expert_elo_votes","value":889,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_expert_elo_interval","value":19.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_expert_elo","value":1473.432031023815,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_expert_elo_votes","value":722,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_expert_elo_interval","value":21.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_expert_elo","value":1471.9974096849242,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_expert_elo_votes","value":6161,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_expert_elo_interval","value":7.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_expert_elo","value":1469.8905651031716,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_expert_elo_votes","value":2604,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_expert_elo_interval","value":11.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_expert_elo","value":1467.7776269304409,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_expert_elo_votes","value":3311,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_expert_elo_interval","value":10.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_expert_elo","value":1466.5815695583938,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_expert_elo_votes","value":4725,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_expert_elo_interval","value":9.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_expert_elo","value":1465.8811958657016,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_expert_elo_votes","value":4720,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_expert_elo_interval","value":9.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_expert_elo","value":1465.099865013997,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_expert_elo_votes","value":4821,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_expert_elo_interval","value":9.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_expert_elo","value":1464.4619994011168,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_expert_elo_votes","value":501,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_expert_elo_interval","value":24.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_expert_elo","value":1463.1069279741287,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_expert_elo_votes","value":5913,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_expert_elo_interval","value":8.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_expert_elo","value":1462.826908871089,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_expert_elo_votes","value":423,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_expert_elo_interval","value":28.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_expert_elo","value":1462.5606946635398,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_expert_elo_votes","value":6992,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_expert_elo_interval","value":7.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_expert_elo","value":1461.4422989605016,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_expert_elo_votes","value":10076,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_expert_elo_interval","value":6.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_expert_elo","value":1459.838242362101,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_expert_elo_votes","value":1305,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_expert_elo_interval","value":16.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_expert_elo","value":1458.8148723209013,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_expert_elo_votes","value":4794,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_expert_elo_interval","value":9.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_expert_elo","value":1454.423543376805,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_expert_elo_votes","value":4910,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_expert_elo_interval","value":8.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_expert_elo","value":1453.8179230300452,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_expert_elo_votes","value":2609,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_expert_elo_interval","value":11.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_expert_elo","value":1453.6998477137329,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_expert_elo_votes","value":1210,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_expert_elo_interval","value":16.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_expert_elo","value":1452.076066042975,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_expert_elo_votes","value":8327,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_expert_elo_interval","value":6.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_expert_elo","value":1447.2673212508018,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_expert_elo_votes","value":455,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_expert_elo_interval","value":25.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_expert_elo","value":1445.2215719901415,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_expert_elo_votes","value":4001,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_expert_elo_interval","value":9.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_expert_elo","value":1443.6894995864227,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_expert_elo_votes","value":8487,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_expert_elo_interval","value":7.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_expert_elo","value":1442.7403061595599,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_expert_elo_votes","value":13709,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_expert_elo_interval","value":5.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_expert_elo","value":1442.2258764013823,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_expert_elo_votes","value":754,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_expert_elo_interval","value":21.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_expert_elo","value":1442.0769279055075,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_expert_elo_votes","value":596,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_expert_elo_interval","value":24.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_expert_elo","value":1441.85421883608,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_expert_elo_votes","value":3781,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_expert_elo_interval","value":10.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_expert_elo","value":1441.7607241480384,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_expert_elo_votes","value":6453,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_expert_elo_interval","value":7.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_expert_elo","value":1441.097942849356,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_expert_elo_votes","value":5404,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_expert_elo_interval","value":8.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_expert_elo","value":1437.3832546340072,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_expert_elo_votes","value":1115,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_expert_elo_interval","value":17.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_expert_elo","value":1436.256764246186,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_expert_elo_votes","value":3426,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_expert_elo_interval","value":10.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_expert_elo","value":1434.9410903645664,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_expert_elo_votes","value":6338,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_expert_elo_interval","value":8.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_expert_elo","value":1434.0188709729543,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_expert_elo_votes","value":4189,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_expert_elo_interval","value":9.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_expert_elo","value":1433.1868068689619,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_expert_elo_votes","value":1157,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_expert_elo_interval","value":17.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_expert_elo","value":1432.3419643190239,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_expert_elo_votes","value":1208,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_expert_elo_interval","value":16.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_expert_elo","value":1431.5124438443634,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_expert_elo_votes","value":2063,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_expert_elo_interval","value":12.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_expert_elo","value":1431.1503735422732,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_expert_elo_votes","value":2731,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_expert_elo_interval","value":11.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_expert_elo","value":1427.3165594049917,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_expert_elo_votes","value":2462,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_expert_elo_interval","value":12.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_expert_elo","value":1427.2208317676298,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_expert_elo_votes","value":2654,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_expert_elo_interval","value":11.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_expert_elo","value":1425.8391617867078,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_expert_elo_votes","value":8407,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_expert_elo_interval","value":6.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_expert_elo","value":1425.4337628925853,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_expert_elo_votes","value":4229,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_expert_elo_interval","value":9.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_expert_elo","value":1423.88971336109,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_expert_elo_votes","value":809,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_expert_elo_interval","value":20.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_expert_elo","value":1421.3146668544507,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_expert_elo_votes","value":5330,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_expert_elo_interval","value":8.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_expert_elo","value":1418.9986383273883,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_expert_elo_votes","value":1695,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_expert_elo_interval","value":14.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_expert_elo","value":1416.376917699284,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_expert_elo_votes","value":1096,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_expert_elo_interval","value":17.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_expert_elo","value":1407.8696489534727,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_expert_elo_votes","value":2802,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_expert_elo_interval","value":11.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_expert_elo","value":1407.157770200452,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_expert_elo_votes","value":5839,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_expert_elo_interval","value":8.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_expert_elo","value":1403.5019732781348,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_expert_elo_votes","value":665,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_expert_elo_interval","value":22.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_expert_elo","value":1402.1210185535247,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_expert_elo_votes","value":3020,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_expert_elo_interval","value":11.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_expert_elo","value":1398.0042480538675,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_expert_elo_votes","value":6241,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_expert_elo_interval","value":8.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_expert_elo","value":1397.5690270911396,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_expert_elo_votes","value":658,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_expert_elo_interval","value":21.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_expert_elo","value":1396.33224410155,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_expert_elo_votes","value":1173,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_expert_elo_interval","value":16.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_expert_elo","value":1396.0576411321492,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_expert_elo_votes","value":6384,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_expert_elo_interval","value":8.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_expert_elo","value":1393.666364436795,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_expert_elo_votes","value":886,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_expert_elo_interval","value":19.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_expert_elo","value":1384.5769078580588,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_expert_elo_votes","value":315,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_expert_elo_interval","value":32.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_expert_elo","value":1384.563251249172,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_expert_elo_votes","value":7539,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_expert_elo_interval","value":7.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_expert_elo","value":1378.573786600397,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_expert_elo_votes","value":1229,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_expert_elo_interval","value":17.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_expert_elo","value":1377.999929420524,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_expert_elo_votes","value":3787,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_expert_elo_interval","value":10.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_expert_elo","value":1375.970912322527,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_expert_elo_votes","value":660,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_expert_elo_interval","value":22.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_expert_elo","value":1372.5351402836086,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_expert_elo_votes","value":185,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_expert_elo_interval","value":41.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_expert_elo","value":1370.3329208481268,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_expert_elo_votes","value":1471,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_expert_elo_interval","value":15.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_expert_elo","value":1364.0876781036047,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_expert_elo_votes","value":847,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_expert_elo_interval","value":20.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_expert_elo","value":1363.8793530026585,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_expert_elo_votes","value":2639,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_expert_elo_interval","value":11.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_expert_elo","value":1362.0644129411216,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_expert_elo_votes","value":236,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_expert_elo_interval","value":36.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_expert_elo","value":1361.287602285031,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_expert_elo_votes","value":1330,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_expert_elo_interval","value":16.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_expert_elo","value":1359.699236365385,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_expert_elo_votes","value":2911,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_expert_elo_interval","value":11.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_expert_elo","value":1358.192486977101,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_expert_elo_votes","value":789,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_expert_elo_interval","value":20.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_expert_elo","value":1357.918128924087,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_expert_elo_votes","value":253,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_expert_elo_interval","value":35.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_expert_elo","value":1357.0854560404412,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_expert_elo_votes","value":889,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_expert_elo_interval","value":19.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_expert_elo","value":1356.3327089920506,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_expert_elo_votes","value":1403,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_expert_elo_interval","value":15.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_expert_elo","value":1352.6758862024792,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_expert_elo_votes","value":190,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_expert_elo_interval","value":41.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_expert_elo","value":1350.4576576210993,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_expert_elo_votes","value":2351,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_expert_elo_interval","value":12.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_expert_elo","value":1342.9413017535126,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_expert_elo_votes","value":2330,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_expert_elo_interval","value":12.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_expert_elo","value":1337.9201615546358,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_expert_elo_votes","value":1351,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_expert_elo_interval","value":16.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_expert_elo","value":1337.689000411036,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_expert_elo_votes","value":2026,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_expert_elo_interval","value":12.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_expert_elo","value":1335.956728279209,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_expert_elo_votes","value":300,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_expert_elo_interval","value":32.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_expert_elo","value":1329.3806005929,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_expert_elo_votes","value":2880,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_expert_elo_interval","value":11.36,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_expert_elo","value":1321.2238990943097,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_expert_elo_votes","value":338,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_expert_elo_interval","value":32.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_expert_elo","value":1316.6479157441113,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_expert_elo_votes","value":1632,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_expert_elo_interval","value":14.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_expert_elo","value":1314.3247651538734,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_expert_elo_votes","value":1342,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_expert_elo_interval","value":16.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_expert_elo","value":1303.7847067093821,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_expert_elo_votes","value":2263,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_expert_elo_interval","value":12.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_expert_elo","value":1295.6219412240512,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_expert_elo_votes","value":2885,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_expert_elo_interval","value":11.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_expert_elo","value":1271.3190108218148,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_expert_elo_votes","value":328,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_expert_elo_interval","value":30.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_expert_elo","value":1258.89256068333,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_expert_elo_votes","value":2016,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_expert_elo_interval","value":13.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_expert_elo","value":1257.8392749675759,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_expert_elo_votes","value":506,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_expert_elo_interval","value":26.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_expert_elo","value":1256.9728661182567,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_expert_elo_votes","value":1680,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_expert_elo_interval","value":15.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_expert_elo","value":1249.798815039972,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_expert_elo_votes","value":5887,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_expert_elo_interval","value":10.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_expert_elo","value":1247.568564009368,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_expert_elo_votes","value":186,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_expert_elo_interval","value":40.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_expert_elo","value":1245.1047989144745,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_expert_elo_votes","value":2397,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_expert_elo_interval","value":12.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_expert_elo","value":1240.4338487166415,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_expert_elo_votes","value":2349,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_expert_elo_interval","value":12.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_expert_elo","value":1235.07430987897,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_expert_elo_votes","value":1535,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_expert_elo_interval","value":15.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_expert_elo","value":1234.3345408149337,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_expert_elo_votes","value":3550,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_expert_elo_interval","value":10.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_expert_elo","value":1231.9780251738127,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_expert_elo_votes","value":2505,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_expert_elo_interval","value":12.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_expert_elo","value":1225.2540949502422,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_expert_elo_votes","value":2917,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_expert_elo_interval","value":11.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_expert_elo","value":1222.8390770288897,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_expert_elo_votes","value":208,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_expert_elo_interval","value":40.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_expert_elo","value":1220.3885145892841,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_expert_elo_votes","value":267,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_expert_elo_interval","value":32.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_expert_elo","value":1208.4946313528183,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_expert_elo_votes","value":2924,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_expert_elo_interval","value":11.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_expert_elo","value":1202.6443607925125,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_expert_elo_votes","value":1124,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_expert_elo_interval","value":17.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_expert_elo","value":1201.611780502371,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_expert_elo_votes","value":754,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_expert_elo_interval","value":20.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_expert_elo","value":1173.345083629526,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_expert_elo_votes","value":524,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_expert_elo_interval","value":24.27,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_expert_elo","value":1171.2900120371198,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_expert_elo_votes","value":4025,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_expert_elo_interval","value":10.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_expert_elo","value":1143.8077884456443,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_expert_elo_votes","value":2589,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_expert_elo_interval","value":12.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_expert_elo","value":1137.4579741133664,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_expert_elo_votes","value":604,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_expert_elo_interval","value":21.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_expert_elo","value":1089.9543465668144,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_expert_elo_votes","value":499,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_expert_elo_interval","value":24.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_expert_elo","value":1007.0202945149049,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_expert_elo_votes","value":487,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_expert_elo_interval","value":26.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_hard_prompts_english_elo","value":1547.524834306811,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":1208,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":17.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_hard_prompts_english_elo","value":1533.1017302597384,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":1990,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":13.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_hard_prompts_english_elo","value":1531.0670495489885,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":23259,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":5.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_hard_prompts_english_elo","value":1523.2100647303314,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":8411,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":7.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_hard_prompts_english_elo","value":1521.2620026985842,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":3454,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":10.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_hard_prompts_english_elo","value":1519.1025663075093,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":940,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":18.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_hard_prompts_english_elo","value":1510.9249955822047,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":838,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":20.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_hard_prompts_english_elo","value":1510.2578089161948,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":11708,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":6.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_hard_prompts_english_elo","value":1508.1151158695388,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":20836,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":5.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_hard_prompts_english_elo","value":1503.712054444271,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":7058,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":7.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_hard_prompts_english_elo","value":1503.6139019979164,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":9477,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":7.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_hard_prompts_english_elo","value":1502.7176639199229,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":1606,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":15.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_hard_prompts_english_elo","value":1496.436022814201,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":4471,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":9.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_hard_prompts_english_elo","value":1495.9948468708203,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":8025,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":7.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_hard_prompts_english_elo","value":1495.4406808516233,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":2531,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":12.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_hard_prompts_english_elo","value":1494.3204825319071,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":21379,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":5.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_hard_prompts_english_elo","value":1493.5420610712758,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":21356,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":5.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_hard_prompts_english_elo","value":1490.0777556911344,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":7713,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":7.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_hard_prompts_english_elo","value":1489.466389919156,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":2119,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":12.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_hard_prompts_english_elo","value":1487.2457926000739,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":7112,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":7.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_hard_prompts_english_elo","value":1486.7361343178418,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":18817,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":5.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_hard_prompts_english_elo","value":1484.1514153375701,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":10143,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":6.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_hard_prompts_english_elo","value":1483.8023214312325,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":21960,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":5.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_hard_prompts_english_elo","value":1482.4932447534588,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":13789,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":6.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_hard_prompts_english_elo","value":1481.7703309523558,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":17950,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":5.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_hard_prompts_english_elo","value":1481.7589718758322,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":18759,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":5.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_hard_prompts_english_elo","value":1481.035491326053,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":11440,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":6.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_hard_prompts_english_elo","value":1480.4455587648958,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":37273,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":4.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_hard_prompts_english_elo","value":1478.8027661136684,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":19722,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":5.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_hard_prompts_english_elo","value":1476.8514981924777,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":10621,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":6.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_hard_prompts_english_elo","value":1471.0788839206325,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":12479,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":6.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_hard_prompts_english_elo","value":1470.094472193748,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":21308,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":4.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_hard_prompts_english_elo","value":1466.0466838598354,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":17840,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":5.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_hard_prompts_english_elo","value":1464.836132008083,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":13726,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":6.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_hard_prompts_english_elo","value":1464.3388590245336,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":11309,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":6.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_hard_prompts_english_elo","value":1464.089351040243,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":10737,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":6.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_hard_prompts_english_elo","value":1462.3683175580595,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":8812,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":6.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_hard_prompts_english_elo","value":1460.6554966931649,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":15076,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":6.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_hard_prompts_english_elo","value":1460.2138638254646,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":12153,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":6.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_hard_prompts_english_elo","value":1460.2073731644823,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":10955,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":6.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_hard_prompts_english_elo","value":1460.1849955839816,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":5852,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":8.27,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_hard_prompts_english_elo","value":1460.0362185312847,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":8279,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":6.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_hard_prompts_english_elo","value":1456.5470174406191,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":2950,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_hard_prompts_english_elo","value":1456.355550320313,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":1332,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":15.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_hard_prompts_english_elo","value":1455.583111155168,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":18062,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":5.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_hard_prompts_english_elo","value":1455.2934713812633,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":15359,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":6.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_hard_prompts_english_elo","value":1454.7149615602912,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":1650,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":14.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_hard_prompts_english_elo","value":1453.132604389261,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":3126,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":10.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_hard_prompts_english_elo","value":1452.5279120383138,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":28963,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":4.08,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_hard_prompts_english_elo","value":1452.369275795364,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":2699,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":11.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_hard_prompts_english_elo","value":1450.1553097669866,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":27732,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":4.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_hard_prompts_english_elo","value":1449.3900048300475,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":10833,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":6.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_hard_prompts_english_elo","value":1448.9245212392484,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":16226,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":6.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_hard_prompts_english_elo","value":1448.137889411124,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":1277,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":15.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_hard_prompts_english_elo","value":1447.8364480469882,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":16447,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":5.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_hard_prompts_english_elo","value":1445.389635737521,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":11113,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":6.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_hard_prompts_english_elo","value":1445.2819734431814,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":3851,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":10.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_hard_prompts_english_elo","value":1444.8023954347027,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":8254,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":6.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_hard_prompts_english_elo","value":1444.4177444803186,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":7574,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":7.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_hard_prompts_english_elo","value":1441.8954828474712,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":1858,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":13.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_hard_prompts_english_elo","value":1441.350380307024,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":23721,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":5.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_hard_prompts_english_elo","value":1439.916749054847,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":9647,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":6.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_hard_prompts_english_elo","value":1439.1374274579453,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":2499,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":12.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_hard_prompts_english_elo","value":1436.9010446412026,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":2766,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":11.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_hard_prompts_english_elo","value":1436.091693129711,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":22730,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":4.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_hard_prompts_english_elo","value":1434.3963673080511,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":40648,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":3.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_hard_prompts_english_elo","value":1431.2515031904868,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":1717,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":14.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_hard_prompts_english_elo","value":1430.941576798623,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":8668,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":6.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_hard_prompts_english_elo","value":1430.896395640732,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":5216,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":8.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_hard_prompts_english_elo","value":1430.5389374896708,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":13040,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":5.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_hard_prompts_english_elo","value":1429.2834809373107,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":4832,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":8.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_hard_prompts_english_elo","value":1428.6168099284873,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":8663,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":7.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_hard_prompts_english_elo","value":1428.4345893145342,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":8348,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":6.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_hard_prompts_english_elo","value":1428.1886302786065,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":5470,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":8.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_hard_prompts_english_elo","value":1426.9188199361297,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":2803,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":11.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_hard_prompts_english_elo","value":1421.6591528578174,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":3106,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":10.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_hard_prompts_english_elo","value":1420.7040818026776,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":16241,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":5.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_hard_prompts_english_elo","value":1420.2398612603965,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":28916,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":4.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_hard_prompts_english_elo","value":1419.7855714593802,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":19862,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":5.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_hard_prompts_english_elo","value":1419.4041529477854,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":6658,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":7.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_hard_prompts_english_elo","value":1410.5620003507834,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":12107,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":6.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_hard_prompts_english_elo","value":1410.4561895071529,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":8846,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":6.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_hard_prompts_english_elo","value":1408.708880656407,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":18209,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":5.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_hard_prompts_english_elo","value":1406.696892799113,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":850,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":19.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_hard_prompts_english_elo","value":1406.4214507768534,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":4749,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":8.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_hard_prompts_english_elo","value":1403.1682727828643,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":19973,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":5.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_hard_prompts_english_elo","value":1401.7257612785602,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":22457,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":5.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_hard_prompts_english_elo","value":1397.282507382777,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":1768,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":13.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_hard_prompts_english_elo","value":1392.8864384020794,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":10446,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":6.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_hard_prompts_english_elo","value":1390.9642700146378,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":642,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":22.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_hard_prompts_english_elo","value":1387.6847913488175,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":6577,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":7.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_hard_prompts_english_elo","value":1387.3365314264454,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":19941,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":5.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_hard_prompts_english_elo","value":1385.2496014325332,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":2748,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":11.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_hard_prompts_english_elo","value":1384.0608638983992,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":3016,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":10.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_hard_prompts_english_elo","value":1383.630679416498,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":12199,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":6.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_hard_prompts_english_elo","value":1382.7922365396366,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":5602,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":8.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_hard_prompts_english_elo","value":1380.2341290846612,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":5143,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":8.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_hard_prompts_english_elo","value":1378.8437458818225,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":9015,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":6.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_hard_prompts_english_elo","value":1375.8092940922968,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":1650,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":14.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_hard_prompts_english_elo","value":1375.2760808832866,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":2944,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":10.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_hard_prompts_english_elo","value":1373.431553716925,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":726,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":21.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_hard_prompts_english_elo","value":1371.9247782859788,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":4238,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":9.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_hard_prompts_english_elo","value":1369.2447624956944,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":2559,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":11.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_hard_prompts_english_elo","value":1367.968097418624,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":6482,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":7.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_hard_prompts_english_elo","value":1365.7350765012516,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":9119,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":6.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_hard_prompts_english_elo","value":1362.0965528721883,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":7672,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":7.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_hard_prompts_english_elo","value":1357.1328121720117,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":1009,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":18.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_hard_prompts_english_elo","value":1356.114126789018,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":9945,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":7.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_hard_prompts_english_elo","value":1353.292553372021,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":6995,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":7.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_hard_prompts_english_elo","value":1353.040838880966,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":8932,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":6.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_hard_prompts_english_elo","value":1349.4433664268058,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":729,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":20.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_hard_prompts_english_elo","value":1344.514168486678,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":904,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":20.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_hard_prompts_english_elo","value":1342.6532103169948,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":10232,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":6.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_hard_prompts_english_elo","value":1338.5042962672346,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":1694,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":14.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_hard_prompts_english_elo","value":1335.0153058497651,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":11259,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":6.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_hard_prompts_english_elo","value":1328.7927671188036,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":5161,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":8.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_hard_prompts_english_elo","value":1318.0847046814122,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":700,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":20.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_hard_prompts_english_elo","value":1295.3514775182139,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":7692,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":7.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_hard_prompts_english_elo","value":1292.9450373286732,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":5735,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":8.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_hard_prompts_english_elo","value":1292.525687123117,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":19579,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":6.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_hard_prompts_english_elo","value":1292.449751260795,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":1062,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":16.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_hard_prompts_english_elo","value":1291.9510341690293,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":2081,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":13.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_hard_prompts_english_elo","value":1289.5889086286438,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":6529,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":7.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_hard_prompts_english_elo","value":1279.2491249193959,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":6208,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":7.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_hard_prompts_english_elo","value":1278.2982734540942,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":11355,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":6.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_hard_prompts_english_elo","value":1276.7181042962984,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":8010,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":7.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_hard_prompts_english_elo","value":1276.5890274185272,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":9544,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":6.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_hard_prompts_english_elo","value":1269.0833944459812,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":759,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":19.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_hard_prompts_english_elo","value":1268.9743448399126,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":7818,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":7.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_hard_prompts_english_elo","value":1261.0988125878011,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":9133,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":7.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_hard_prompts_english_elo","value":1253.121876232504,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":764,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":20.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_hard_prompts_english_elo","value":1242.9731213654459,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":2355,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":11.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_hard_prompts_english_elo","value":1229.7427219123956,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":3804,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":9.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_hard_prompts_english_elo","value":1205.64229950568,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":12606,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":6.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_hard_prompts_english_elo","value":1195.4316122464447,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":8195,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":7.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_hard_prompts_english_elo","value":1194.1912706624253,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":1735,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":13.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_hard_prompts_english_elo","value":1170.6349320987854,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":1822,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":12.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_hard_prompts_english_elo","value":1140.6863274954649,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":1377,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":14.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_hard_prompts_english_elo","value":1086.6019776481362,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_hard_prompts_english_elo_votes","value":1437,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_hard_prompts_english_elo_interval","value":14.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_software_elo","value":1555.8592256942788,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_software_elo_votes","value":1822,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_software_elo_interval","value":14.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_software_elo","value":1538.0925825776296,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_software_elo_votes","value":2904,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_software_elo_interval","value":11.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_software_elo","value":1529.241386663625,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_software_elo_votes","value":4818,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_software_elo_interval","value":9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_software_elo","value":1527.7736356645082,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_software_elo_votes","value":33580,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_software_elo_interval","value":4.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_software_elo","value":1526.9912957425017,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_software_elo_votes","value":24848,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_software_elo_interval","value":5.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_software_elo","value":1526.9909273454014,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_software_elo_votes","value":1648,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_software_elo_interval","value":14.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_software_elo","value":1517.6413620628664,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_software_elo_votes","value":1158,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_software_elo_interval","value":17.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_software_elo","value":1516.2750732657694,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_software_elo_votes","value":26175,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_software_elo_interval","value":5.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_software_elo","value":1512.14401536554,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_software_elo_votes","value":15669,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_software_elo_interval","value":5.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_software_elo","value":1510.841659670412,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_software_elo_votes","value":6549,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_software_elo_interval","value":7.89,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_software_elo","value":1505.9575541889328,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_software_elo_votes","value":14131,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_software_elo_interval","value":6.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_software_elo","value":1505.7855944112277,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_software_elo_votes","value":3124,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_software_elo_interval","value":10.89,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_software_elo","value":1501.2895826120325,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_software_elo_votes","value":2359,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_software_elo_interval","value":12.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_software_elo","value":1500.5560977764055,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_software_elo_votes","value":12400,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_software_elo_interval","value":6.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_software_elo","value":1498.598701775604,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_software_elo_votes","value":4122,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_software_elo_interval","value":9.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_software_elo","value":1498.4454997838336,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_software_elo_votes","value":12508,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_software_elo_interval","value":6.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_software_elo","value":1497.8948503346523,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_software_elo_votes","value":10449,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_software_elo_interval","value":6.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_software_elo","value":1497.6504681183137,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_software_elo_votes","value":16613,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_software_elo_interval","value":5.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_software_elo","value":1497.564621007433,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_software_elo_votes","value":11018,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_software_elo_interval","value":6.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_software_elo","value":1495.6609356657739,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_software_elo_votes","value":29693,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_software_elo_interval","value":4.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_software_elo","value":1494.0859293209962,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_software_elo_votes","value":19417,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_software_elo_interval","value":5.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_software_elo","value":1492.7423473821273,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_software_elo_votes","value":27462,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_software_elo_interval","value":4.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_software_elo","value":1492.1401702052522,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_software_elo_votes","value":14513,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_software_elo_interval","value":5.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_software_elo","value":1491.3687150936364,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_software_elo_votes","value":27745,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_software_elo_interval","value":4.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_software_elo","value":1491.3585363247378,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_software_elo_votes","value":25473,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_software_elo_interval","value":5.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_software_elo","value":1489.224890487188,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_software_elo_votes","value":15703,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_software_elo_interval","value":5.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_software_elo","value":1488.1208824441421,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_software_elo_votes","value":25123,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_software_elo_interval","value":5.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_software_elo","value":1486.75215185109,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_software_elo_votes","value":50148,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_software_elo_interval","value":4.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_software_elo","value":1483.924052237785,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_software_elo_votes","value":16046,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_software_elo_interval","value":5.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_software_elo","value":1483.2496351316674,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_software_elo_votes","value":24729,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_software_elo_interval","value":4.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_software_elo","value":1483.2114254657674,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_software_elo_votes","value":26901,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_software_elo_interval","value":4.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_software_elo","value":1480.761751405022,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_software_elo_votes","value":16699,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_software_elo_interval","value":5.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_software_elo","value":1477.8205613984514,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_software_elo_votes","value":9127,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_software_elo_interval","value":6.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_software_elo","value":1476.563507275472,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_software_elo_votes","value":2626,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_software_elo_interval","value":11.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_software_elo","value":1474.1739895408703,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_software_elo_votes","value":19172,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_software_elo_interval","value":5.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_software_elo","value":1472.9146213288896,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_software_elo_votes","value":17150,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_software_elo_interval","value":5.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_software_elo","value":1472.447482936533,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_software_elo_votes","value":30336,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_software_elo_interval","value":4.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_software_elo","value":1470.854082241388,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_software_elo_votes","value":15966,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_software_elo_interval","value":5.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_software_elo","value":1468.950241038787,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_software_elo_votes","value":23637,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_software_elo_interval","value":5.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_software_elo","value":1468.134513431794,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_software_elo_votes","value":2593,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_software_elo_interval","value":11.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_software_elo","value":1467.3502911746239,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_software_elo_votes","value":25769,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_software_elo_interval","value":5.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_software_elo","value":1465.1804775875737,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_software_elo_votes","value":15820,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_software_elo_interval","value":5.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_software_elo","value":1463.468696329406,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_software_elo_votes","value":15935,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_software_elo_interval","value":5.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_software_elo","value":1463.4309783719186,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_software_elo_votes","value":2224,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_software_elo_interval","value":11.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_software_elo","value":1463.1943814829608,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_software_elo_votes","value":37377,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_software_elo_interval","value":4.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_software_elo","value":1463.077900077478,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_software_elo_votes","value":4830,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_software_elo_interval","value":8.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_software_elo","value":1462.8908492754244,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_software_elo_votes","value":19301,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_software_elo_interval","value":5.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_software_elo","value":1461.741829156052,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_software_elo_votes","value":20160,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_software_elo_interval","value":5.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_software_elo","value":1460.2942565857152,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_software_elo_votes","value":4159,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_software_elo_interval","value":9.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_software_elo","value":1460.0204103991011,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_software_elo_votes","value":11159,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_software_elo_interval","value":6.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_software_elo","value":1459.1104390353464,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_software_elo_votes","value":44050,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_software_elo_interval","value":3.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_software_elo","value":1458.392427562563,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_software_elo_votes","value":4593,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_software_elo_interval","value":9.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_software_elo","value":1456.6292907920263,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_software_elo_votes","value":10857,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_software_elo_interval","value":6.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_software_elo","value":1455.2593074726815,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_software_elo_votes","value":12610,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_software_elo_interval","value":5.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_software_elo","value":1453.8896591112616,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_software_elo_votes","value":14122,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_software_elo_interval","value":5.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_software_elo","value":1453.6123238087243,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_software_elo_votes","value":2214,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_software_elo_interval","value":11.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_software_elo","value":1453.510763472388,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_software_elo_votes","value":4126,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_software_elo_interval","value":9.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_software_elo","value":1452.8491590555386,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_software_elo_votes","value":21378,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_software_elo_interval","value":5.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_software_elo","value":1451.6219915892784,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_software_elo_votes","value":26055,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_software_elo_interval","value":4.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_software_elo","value":1449.9877406633768,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_software_elo_votes","value":14375,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_software_elo_interval","value":6.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_software_elo","value":1447.1490943356987,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_software_elo_votes","value":12584,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_software_elo_interval","value":6.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_software_elo","value":1446.9918408677083,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_software_elo_votes","value":8050,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_software_elo_interval","value":6.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_software_elo","value":1446.502859743058,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_software_elo_votes","value":34910,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_software_elo_interval","value":3.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_software_elo","value":1445.9527537588174,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_software_elo_votes","value":34214,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_software_elo_interval","value":4.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_software_elo","value":1443.6727503442817,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_software_elo_votes","value":17256,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_software_elo_interval","value":5.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_software_elo","value":1441.9817561186442,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_software_elo_votes","value":4005,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_software_elo_interval","value":10.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_software_elo","value":1440.423400131152,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_software_elo_votes","value":8092,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_software_elo_interval","value":7.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_software_elo","value":1438.9192381546327,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_software_elo_votes","value":56191,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_software_elo_interval","value":3.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_software_elo","value":1436.6742533768795,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_software_elo_votes","value":11701,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_software_elo_interval","value":6.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_software_elo","value":1436.0294908539004,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_software_elo_votes","value":25039,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_software_elo_interval","value":5.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_software_elo","value":1435.9992980022434,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_software_elo_votes","value":4148,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_software_elo_interval","value":9.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_software_elo","value":1434.7928928569247,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_software_elo_votes","value":5530,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_software_elo_interval","value":8.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_software_elo","value":1434.3058595334055,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_software_elo_votes","value":22765,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_software_elo_interval","value":4.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_software_elo","value":1434.2258158478978,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_software_elo_votes","value":18421,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_software_elo_interval","value":5.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_software_elo","value":1431.7171860833248,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_software_elo_votes","value":8127,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_software_elo_interval","value":7.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_software_elo","value":1431.1447680700614,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_software_elo_votes","value":11357,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_software_elo_interval","value":6.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_software_elo","value":1430.8538657033985,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_software_elo_votes","value":2910,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_software_elo_interval","value":10.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_software_elo","value":1425.08089007731,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_software_elo_votes","value":43860,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_software_elo_interval","value":3.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_software_elo","value":1422.5250200802502,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_software_elo_votes","value":4071,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_software_elo_interval","value":9.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_software_elo","value":1420.1297597897276,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_software_elo_votes","value":10822,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_software_elo_interval","value":6.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_software_elo","value":1416.6165811161932,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_software_elo_votes","value":7962,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_software_elo_interval","value":7.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_software_elo","value":1416.3385606222137,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_software_elo_votes","value":25042,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_software_elo_interval","value":5.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_software_elo","value":1415.9233920159625,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_software_elo_votes","value":28538,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_software_elo_interval","value":4.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_software_elo","value":1415.153519606583,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_software_elo_votes","value":12054,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_software_elo_interval","value":6.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_software_elo","value":1414.7490031521565,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_software_elo_votes","value":19145,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_software_elo_interval","value":5.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_software_elo","value":1413.0884827345453,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_software_elo_votes","value":25399,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_software_elo_interval","value":5.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_software_elo","value":1409.5451069085495,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_software_elo_votes","value":1279,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_software_elo_interval","value":16.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_software_elo","value":1409.3567424660116,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_software_elo_votes","value":2836,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_software_elo_interval","value":10.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_software_elo","value":1402.0999667835656,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_software_elo_votes","value":24954,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_software_elo_interval","value":5.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_software_elo","value":1401.1510202925028,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_software_elo_votes","value":10457,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_software_elo_interval","value":6.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_software_elo","value":1394.4241755144221,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_software_elo_votes","value":4306,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_software_elo_interval","value":9.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_software_elo","value":1393.7316605596889,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_software_elo_votes","value":8921,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_software_elo_interval","value":6.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_software_elo","value":1393.4212232295843,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_software_elo_votes","value":4736,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_software_elo_interval","value":8.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_software_elo","value":1392.7900424198488,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_software_elo_votes","value":8458,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_software_elo_interval","value":7.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_software_elo","value":1391.319560885859,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_software_elo_votes","value":16447,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_software_elo_interval","value":5.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_software_elo","value":1390.8673402612205,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_software_elo_votes","value":935,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_software_elo_interval","value":18.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_software_elo","value":1388.9193087774288,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_software_elo_votes","value":4289,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_software_elo_interval","value":8.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_software_elo","value":1387.5056537139003,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_software_elo_votes","value":10219,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_software_elo_interval","value":6.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_software_elo","value":1384.4717895054423,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_software_elo_votes","value":1114,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_software_elo_interval","value":17.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_software_elo","value":1382.9098464903711,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_software_elo_votes","value":16498,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_software_elo_interval","value":5.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_software_elo","value":1377.8803553189246,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_software_elo_votes","value":14363,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_software_elo_interval","value":5.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_software_elo","value":1372.4865753591637,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_software_elo_votes","value":2455,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_software_elo_interval","value":11.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_software_elo","value":1367.1538133256558,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_software_elo_votes","value":1166,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_software_elo_interval","value":17.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_software_elo","value":1367.019823615186,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_software_elo_votes","value":14699,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_software_elo_interval","value":5.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_software_elo","value":1366.3542962395509,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_software_elo_votes","value":6584,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_software_elo_interval","value":7.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_software_elo","value":1365.9134297609105,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_software_elo_votes","value":843,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_software_elo_interval","value":19.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_software_elo","value":1363.7434576541384,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_software_elo_votes","value":4338,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_software_elo_interval","value":9.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_software_elo","value":1362.2335480514496,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_software_elo_votes","value":12293,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_software_elo_interval","value":6.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_software_elo","value":1360.1184042263696,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_software_elo_votes","value":12397,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_software_elo_interval","value":6.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_software_elo","value":1359.1879608565464,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_software_elo_votes","value":11210,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_software_elo_interval","value":6.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_software_elo","value":1354.0455280925532,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_software_elo_votes","value":14077,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_software_elo_interval","value":5.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_software_elo","value":1352.5586747704651,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_software_elo_votes","value":1694,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_software_elo_interval","value":14.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_software_elo","value":1345.115361562144,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_software_elo_votes","value":2809,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_software_elo_interval","value":11.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_software_elo","value":1343.8311803505212,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_software_elo_votes","value":16581,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_software_elo_interval","value":5.27,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_software_elo","value":1339.7560087688719,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_software_elo_votes","value":8148,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_software_elo_interval","value":6.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_software_elo","value":1336.4429471050403,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_software_elo_votes","value":17971,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_software_elo_interval","value":5.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_software_elo","value":1312.8783204237643,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_software_elo_votes","value":867,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_software_elo_interval","value":18.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_software_elo","value":1311.0941985783625,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_software_elo_votes","value":3591,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_software_elo_interval","value":10.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_software_elo","value":1304.7837445048456,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_software_elo_votes","value":1454,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_software_elo_interval","value":14.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_software_elo","value":1301.3148961458935,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_software_elo_votes","value":10904,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_software_elo_interval","value":6.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_software_elo","value":1298.697318895052,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_software_elo_votes","value":12287,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_software_elo_interval","value":6.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_software_elo","value":1297.236832100669,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_software_elo_votes","value":31401,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_software_elo_interval","value":5.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_software_elo","value":1292.1418227337417,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_software_elo_votes","value":10448,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_software_elo_interval","value":6.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_software_elo","value":1290.7227731906542,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_software_elo_votes","value":17795,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_software_elo_interval","value":5.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_software_elo","value":1285.677534826635,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_software_elo_votes","value":9503,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_software_elo_interval","value":6.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_software_elo","value":1277.5745957759614,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_software_elo_votes","value":11864,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_software_elo_interval","value":6.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_software_elo","value":1276.0887317723889,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_software_elo_votes","value":12143,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_software_elo_interval","value":6.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_software_elo","value":1272.9199439640972,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_software_elo_votes","value":14851,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_software_elo_interval","value":5.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_software_elo","value":1268.6550700468724,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_software_elo_votes","value":986,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_software_elo_interval","value":18.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_software_elo","value":1260.9380959387897,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_software_elo_votes","value":1381,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_software_elo_interval","value":14.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_software_elo","value":1259.8301722081546,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_software_elo_votes","value":14811,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_software_elo_interval","value":6.08,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_software_elo","value":1248.1068498902841,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_software_elo_votes","value":3478,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_software_elo_interval","value":9.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_software_elo","value":1227.885814317172,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_software_elo_votes","value":19950,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_software_elo_interval","value":5.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_software_elo","value":1227.7916268651663,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_software_elo_votes","value":5580,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_software_elo_interval","value":8.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_software_elo","value":1197.0116000791036,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_software_elo_votes","value":2714,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_software_elo_interval","value":11.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_software_elo","value":1194.934185931086,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_software_elo_votes","value":13139,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_software_elo_interval","value":6.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_software_elo","value":1173.5747366616497,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_software_elo_votes","value":2845,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_software_elo_interval","value":10.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_software_elo","value":1103.249412073082,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_software_elo_votes","value":2165,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_software_elo_interval","value":12.89,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_software_elo","value":1056.2240002864805,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_software_elo_votes","value":2184,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_software_elo_interval","value":13.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_mathematical_elo","value":1556.459495842255,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_mathematical_elo_votes","value":328,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_mathematical_elo_interval","value":31.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_mathematical_elo","value":1543.750693228717,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_mathematical_elo_votes","value":3767,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_mathematical_elo_interval","value":10.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_mathematical_elo","value":1536.937985922743,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_mathematical_elo_votes","value":818,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_mathematical_elo_interval","value":21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_mathematical_elo","value":1526.2821332407023,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_mathematical_elo_votes","value":4247,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_mathematical_elo_interval","value":9.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_mathematical_elo","value":1515.0603776734545,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_mathematical_elo_votes","value":2424,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_mathematical_elo_interval","value":12.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_mathematical_elo","value":1512.9243648560832,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_mathematical_elo_votes","value":2221,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_mathematical_elo_interval","value":13.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_mathematical_elo","value":1511.248004458339,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_mathematical_elo_votes","value":228,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_mathematical_elo_interval","value":38.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_mathematical_elo","value":1509.2357725703714,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_mathematical_elo_votes","value":3651,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_mathematical_elo_interval","value":10.6,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_mathematical_elo","value":1506.2777955258919,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_mathematical_elo_votes","value":362,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_mathematical_elo_interval","value":30.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_mathematical_elo","value":1505.6182738873401,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_mathematical_elo_votes","value":1737,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_mathematical_elo_interval","value":14.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_mathematical_elo","value":1505.5640171513808,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_mathematical_elo_votes","value":467,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_mathematical_elo_interval","value":26.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_mathematical_elo","value":1501.0772804071685,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_mathematical_elo_votes","value":1672,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_mathematical_elo_interval","value":14.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_mathematical_elo","value":1497.364019377912,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_mathematical_elo_votes","value":3480,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_mathematical_elo_interval","value":10.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_mathematical_elo","value":1496.6426179970429,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_mathematical_elo_votes","value":3544,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_mathematical_elo_interval","value":10.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_mathematical_elo","value":1496.140520014124,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_mathematical_elo_votes","value":3983,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_mathematical_elo_interval","value":10.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_mathematical_elo","value":1495.3364330054446,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_mathematical_elo_votes","value":2244,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_mathematical_elo_interval","value":13.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_mathematical_elo","value":1494.4864507752202,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_mathematical_elo_votes","value":1867,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_mathematical_elo_interval","value":14.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_mathematical_elo","value":1494.309457776248,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_mathematical_elo_votes","value":2700,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_mathematical_elo_interval","value":11.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_mathematical_elo","value":1494.1348821605256,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_mathematical_elo_votes","value":1020,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_mathematical_elo_interval","value":18.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_mathematical_elo","value":1493.9959123682522,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_mathematical_elo_votes","value":1649,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_mathematical_elo_interval","value":14.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_mathematical_elo","value":1492.9098674931488,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_mathematical_elo_votes","value":205,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_mathematical_elo_interval","value":38.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_mathematical_elo","value":1491.085945929331,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_mathematical_elo_votes","value":4099,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_mathematical_elo_interval","value":9.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_mathematical_elo","value":1490.4681443630343,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_mathematical_elo_votes","value":2148,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_mathematical_elo_interval","value":13.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_mathematical_elo","value":1490.1333657412874,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_mathematical_elo_votes","value":433,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_mathematical_elo_interval","value":28.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_mathematical_elo","value":1487.007240054485,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_mathematical_elo_votes","value":2459,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_mathematical_elo_interval","value":12.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_mathematical_elo","value":1482.925676848408,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_mathematical_elo_votes","value":3982,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_mathematical_elo_interval","value":10.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_mathematical_elo","value":1481.6920378672007,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_mathematical_elo_votes","value":2702,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_mathematical_elo_interval","value":11.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_mathematical_elo","value":1481.154056877734,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_mathematical_elo_votes","value":2161,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_mathematical_elo_interval","value":13.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_mathematical_elo","value":1480.497695024134,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_mathematical_elo_votes","value":723,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_mathematical_elo_interval","value":21.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_mathematical_elo","value":1479.7033682792885,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_mathematical_elo_votes","value":2199,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_mathematical_elo_interval","value":12.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_mathematical_elo","value":1477.9506436198087,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_mathematical_elo_votes","value":2463,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_mathematical_elo_interval","value":12.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_mathematical_elo","value":1477.6934521805563,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_mathematical_elo_votes","value":7155,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_mathematical_elo_interval","value":7.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_mathematical_elo","value":1476.7781797868902,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_mathematical_elo_votes","value":635,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_mathematical_elo_interval","value":23.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_mathematical_elo","value":1475.3805316397356,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_mathematical_elo_votes","value":311,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_mathematical_elo_interval","value":31.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_mathematical_elo","value":1470.2804598638907,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_mathematical_elo_votes","value":2323,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_mathematical_elo_interval","value":12.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_mathematical_elo","value":1470.1325680327598,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_mathematical_elo_votes","value":2260,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_mathematical_elo_interval","value":12.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_mathematical_elo","value":1469.3783485360848,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_mathematical_elo_votes","value":3412,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_mathematical_elo_interval","value":10.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_mathematical_elo","value":1468.5906858333212,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_mathematical_elo_votes","value":3778,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_mathematical_elo_interval","value":9.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_mathematical_elo","value":1464.9865198708314,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_mathematical_elo_votes","value":345,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_mathematical_elo_interval","value":29.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_mathematical_elo","value":1464.1224106978766,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_mathematical_elo_votes","value":1710,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_mathematical_elo_interval","value":14.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_mathematical_elo","value":1461.6624726014152,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_mathematical_elo_votes","value":1331,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_mathematical_elo_interval","value":16.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_mathematical_elo","value":1460.5221241146864,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_mathematical_elo_votes","value":393,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_mathematical_elo_interval","value":28.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_mathematical_elo","value":1459.7372495161694,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_mathematical_elo_votes","value":2255,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_mathematical_elo_interval","value":12.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_mathematical_elo","value":1455.1636738576128,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_mathematical_elo_votes","value":3288,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_mathematical_elo_interval","value":10.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_mathematical_elo","value":1454.442651579456,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_mathematical_elo_votes","value":6918,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_mathematical_elo_interval","value":7.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_mathematical_elo","value":1453.3974518324464,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_mathematical_elo_votes","value":5472,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_mathematical_elo_interval","value":8.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_mathematical_elo","value":1452.5715351822505,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_mathematical_elo_votes","value":410,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_mathematical_elo_interval","value":28.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_mathematical_elo","value":1451.2639646554514,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_mathematical_elo_votes","value":1593,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_mathematical_elo_interval","value":14.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_mathematical_elo","value":1451.0327453252432,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_mathematical_elo_votes","value":2636,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_mathematical_elo_interval","value":12.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_mathematical_elo","value":1449.0646069853453,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_mathematical_elo_votes","value":1868,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_mathematical_elo_interval","value":13.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_mathematical_elo","value":1448.540316399657,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_mathematical_elo_votes","value":599,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_mathematical_elo_interval","value":23.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_mathematical_elo","value":1448.0936014781332,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_mathematical_elo_votes","value":2875,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_mathematical_elo_interval","value":11.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_mathematical_elo","value":1447.3568876539744,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_mathematical_elo_votes","value":3630,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_mathematical_elo_interval","value":10.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_mathematical_elo","value":1446.6620421730581,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_mathematical_elo_votes","value":1783,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_mathematical_elo_interval","value":13.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_mathematical_elo","value":1446.34783397826,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_mathematical_elo_votes","value":4316,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_mathematical_elo_interval","value":9.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_mathematical_elo","value":1442.3772048576252,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_mathematical_elo_votes","value":2622,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_mathematical_elo_interval","value":11.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_mathematical_elo","value":1440.9575858929315,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_mathematical_elo_votes","value":1748,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_mathematical_elo_interval","value":14.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_mathematical_elo","value":1440.5780680786677,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_mathematical_elo_votes","value":652,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_mathematical_elo_interval","value":22.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_mathematical_elo","value":1440.5423965245157,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_mathematical_elo_votes","value":5215,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_mathematical_elo_interval","value":8.27,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_mathematical_elo","value":1438.9239626298543,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_mathematical_elo_votes","value":2483,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_mathematical_elo_interval","value":12.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_mathematical_elo","value":1437.7523316809643,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_mathematical_elo_votes","value":4519,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_mathematical_elo_interval","value":9.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_mathematical_elo","value":1436.7716040622126,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_mathematical_elo_votes","value":660,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_mathematical_elo_interval","value":21.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_mathematical_elo","value":1435.0692243828378,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_mathematical_elo_votes","value":476,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_mathematical_elo_interval","value":25.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_mathematical_elo","value":1433.8337036996265,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_mathematical_elo_votes","value":1077,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_mathematical_elo_interval","value":17.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_mathematical_elo","value":1433.227664030749,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_mathematical_elo_votes","value":2041,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_mathematical_elo_interval","value":13.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_mathematical_elo","value":1432.3528757309864,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_mathematical_elo_votes","value":2975,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_mathematical_elo_interval","value":11.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_mathematical_elo","value":1430.0215431671497,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_mathematical_elo_votes","value":1260,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_mathematical_elo_interval","value":16.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_mathematical_elo","value":1429.9406111936585,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_mathematical_elo_votes","value":1716,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_mathematical_elo_interval","value":14.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_mathematical_elo","value":1429.592576008286,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_mathematical_elo_votes","value":7959,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_mathematical_elo_interval","value":7.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_mathematical_elo","value":1429.0194604080875,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_mathematical_elo_votes","value":1672,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_mathematical_elo_interval","value":14.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_mathematical_elo","value":1428.7048418361653,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_mathematical_elo_votes","value":3430,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_mathematical_elo_interval","value":10.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_mathematical_elo","value":1425.7873813380581,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_mathematical_elo_votes","value":3909,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_mathematical_elo_interval","value":9.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_mathematical_elo","value":1425.1502962210388,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_mathematical_elo_votes","value":1233,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_mathematical_elo_interval","value":17.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_mathematical_elo","value":1422.65911637655,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_mathematical_elo_votes","value":3457,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_mathematical_elo_interval","value":10.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_mathematical_elo","value":1422.3551375770646,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_mathematical_elo_votes","value":7072,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_mathematical_elo_interval","value":7.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_mathematical_elo","value":1420.7939223953983,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_mathematical_elo_votes","value":3155,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_mathematical_elo_interval","value":10.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_mathematical_elo","value":1419.6944407248116,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_mathematical_elo_votes","value":282,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_mathematical_elo_interval","value":31.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_mathematical_elo","value":1419.214632322619,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_mathematical_elo_votes","value":600,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_mathematical_elo_interval","value":23.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_mathematical_elo","value":1416.9289559528124,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_mathematical_elo_votes","value":3589,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_mathematical_elo_interval","value":10.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_mathematical_elo","value":1415.1942017366214,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_mathematical_elo_votes","value":919,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_mathematical_elo_interval","value":19.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_mathematical_elo","value":1414.3986678445792,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_mathematical_elo_votes","value":635,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_mathematical_elo_interval","value":22.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_mathematical_elo","value":1412.6081397632754,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_mathematical_elo_votes","value":3358,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_mathematical_elo_interval","value":10.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_mathematical_elo","value":1411.4844804789602,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_mathematical_elo_votes","value":625,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_mathematical_elo_interval","value":22.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_mathematical_elo","value":1411.4594831538714,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_mathematical_elo_votes","value":1208,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_mathematical_elo_interval","value":16.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_mathematical_elo","value":1410.3155809785064,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_mathematical_elo_votes","value":1727,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_mathematical_elo_interval","value":14.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_mathematical_elo","value":1408.4829761916596,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_mathematical_elo_votes","value":3479,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_mathematical_elo_interval","value":10.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_mathematical_elo","value":1405.423827234432,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_mathematical_elo_votes","value":446,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_mathematical_elo_interval","value":26.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_mathematical_elo","value":1404.5503953255377,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_mathematical_elo_votes","value":1767,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_mathematical_elo_interval","value":14.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_mathematical_elo","value":1398.4854058262715,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_mathematical_elo_votes","value":1711,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_mathematical_elo_interval","value":13.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_mathematical_elo","value":1397.1949306083247,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_mathematical_elo_votes","value":3938,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_mathematical_elo_interval","value":10.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_mathematical_elo","value":1395.5392154113138,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_mathematical_elo_votes","value":1464,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_mathematical_elo_interval","value":15.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_mathematical_elo","value":1389.654138062328,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_mathematical_elo_votes","value":688,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_mathematical_elo_interval","value":22.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_mathematical_elo","value":1389.5425590928999,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_mathematical_elo_votes","value":2644,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_mathematical_elo_interval","value":11.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_mathematical_elo","value":1386.3365268722762,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_mathematical_elo_votes","value":1550,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_mathematical_elo_interval","value":14.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_mathematical_elo","value":1380.1336005907726,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_mathematical_elo_votes","value":1304,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_mathematical_elo_interval","value":16.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_mathematical_elo","value":1378.9918650478726,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_mathematical_elo_votes","value":2781,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_mathematical_elo_interval","value":10.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_mathematical_elo","value":1378.721544727012,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_mathematical_elo_votes","value":4357,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_mathematical_elo_interval","value":8.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_mathematical_elo","value":1378.1395324248736,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_mathematical_elo_votes","value":2412,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_mathematical_elo_interval","value":12.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_mathematical_elo","value":1369.393398390401,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_mathematical_elo_votes","value":515,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_mathematical_elo_interval","value":24.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_mathematical_elo","value":1368.526820503495,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_mathematical_elo_votes","value":644,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_mathematical_elo_interval","value":23.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_mathematical_elo","value":1368.098543504765,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_mathematical_elo_votes","value":301,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_mathematical_elo_interval","value":32.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_mathematical_elo","value":1366.6977258198322,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_mathematical_elo_votes","value":1444,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_mathematical_elo_interval","value":15.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_mathematical_elo","value":1364.1414148651454,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_mathematical_elo_votes","value":2947,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_mathematical_elo_interval","value":10.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_mathematical_elo","value":1363.261367404529,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_mathematical_elo_votes","value":1577,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_mathematical_elo_interval","value":14.36,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_mathematical_elo","value":1363.119638394038,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_mathematical_elo_votes","value":1766,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_mathematical_elo_interval","value":13.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_mathematical_elo","value":1359.5997740625376,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_mathematical_elo_votes","value":3085,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_mathematical_elo_interval","value":10.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_mathematical_elo","value":1351.6480479316635,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_mathematical_elo_votes","value":1755,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_mathematical_elo_interval","value":15.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_mathematical_elo","value":1346.6452136542412,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_mathematical_elo_votes","value":2478,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_mathematical_elo_interval","value":11.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_mathematical_elo","value":1335.9057728980576,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_mathematical_elo_votes","value":333,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_mathematical_elo_interval","value":29.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_mathematical_elo","value":1335.5735508460555,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_mathematical_elo_votes","value":226,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_mathematical_elo_interval","value":37.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_mathematical_elo","value":1327.313635186904,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_mathematical_elo_votes","value":3211,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_mathematical_elo_interval","value":10.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_mathematical_elo","value":1325.9895391505854,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_mathematical_elo_votes","value":440,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_mathematical_elo_interval","value":28.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_mathematical_elo","value":1312.1122057512673,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_mathematical_elo_votes","value":3654,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_mathematical_elo_interval","value":9.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_mathematical_elo","value":1305.2250385628056,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_mathematical_elo_votes","value":585,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_mathematical_elo_interval","value":24.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_mathematical_elo","value":1294.5302831750737,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_mathematical_elo_votes","value":2569,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_mathematical_elo_interval","value":11.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_mathematical_elo","value":1290.4321953121307,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_mathematical_elo_votes","value":4565,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_mathematical_elo_interval","value":8.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_mathematical_elo","value":1285.5355357943602,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_mathematical_elo_votes","value":1804,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_mathematical_elo_interval","value":13.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_mathematical_elo","value":1284.2631895053232,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_mathematical_elo_votes","value":13306,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_mathematical_elo_interval","value":7.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_mathematical_elo","value":1283.209124575279,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_mathematical_elo_votes","value":5805,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_mathematical_elo_interval","value":8.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_mathematical_elo","value":1274.43572421695,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_mathematical_elo_votes","value":534,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_mathematical_elo_interval","value":23.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_mathematical_elo","value":1271.390045123052,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_mathematical_elo_votes","value":7966,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_mathematical_elo_interval","value":7.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_mathematical_elo","value":1271.144130595198,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_mathematical_elo_votes","value":1934,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_mathematical_elo_interval","value":13.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_mathematical_elo","value":1267.0622024434447,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_mathematical_elo_votes","value":5237,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_mathematical_elo_interval","value":8.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_mathematical_elo","value":1265.3634593341635,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_mathematical_elo_votes","value":5745,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_mathematical_elo_interval","value":8.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_mathematical_elo","value":1255.9920361859438,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_mathematical_elo_votes","value":365,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_mathematical_elo_interval","value":29.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_mathematical_elo","value":1253.9385145074787,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_mathematical_elo_votes","value":2350,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_mathematical_elo_interval","value":11.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_mathematical_elo","value":1253.4334306610726,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_mathematical_elo_votes","value":6524,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_mathematical_elo_interval","value":8.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_mathematical_elo","value":1243.1839912028647,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_mathematical_elo_votes","value":619,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_mathematical_elo_interval","value":20.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_mathematical_elo","value":1243.1671995008812,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_mathematical_elo_votes","value":1447,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_mathematical_elo_interval","value":14.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_mathematical_elo","value":1221.4192506354098,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_mathematical_elo_votes","value":8869,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_mathematical_elo_interval","value":7.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_mathematical_elo","value":1197.8632263208842,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_mathematical_elo_votes","value":1243,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_mathematical_elo_interval","value":14.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_mathematical_elo","value":1180.154256060623,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_mathematical_elo_votes","value":5985,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_mathematical_elo_interval","value":8.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_mathematical_elo","value":1165.4920776910847,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_mathematical_elo_votes","value":1361,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_mathematical_elo_interval","value":14.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_mathematical_elo","value":1128.4259791183676,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_mathematical_elo_votes","value":980,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_mathematical_elo_interval","value":16.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_mathematical_elo","value":1097.9572607580074,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_mathematical_elo_votes","value":976,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_mathematical_elo_interval","value":17.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_science_elo","value":1547.8169904817091,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_science_elo_votes","value":819,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_science_elo_interval","value":21.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_science_elo","value":1532.2313295310723,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_science_elo_votes","value":2440,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_science_elo_interval","value":12.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_science_elo","value":1530.6571483199973,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_science_elo_votes","value":5481,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_science_elo_interval","value":8.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_science_elo","value":1521.7295626277844,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_science_elo_votes","value":1439,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_science_elo_interval","value":16.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_science_elo","value":1520.9576463028611,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_science_elo_votes","value":6186,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_science_elo_interval","value":8.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_science_elo","value":1519.5659119031602,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_science_elo_votes","value":13562,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_science_elo_interval","value":6.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_science_elo","value":1511.43933168469,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_science_elo_votes","value":4337,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_science_elo_interval","value":9.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_science_elo","value":1510.2961108332347,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_science_elo_votes","value":4565,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_science_elo_interval","value":9.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_science_elo","value":1510.171667917115,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_science_elo_votes","value":521,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_science_elo_interval","value":25.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_science_elo","value":1507.9489112366407,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_science_elo_votes","value":11043,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_science_elo_interval","value":6.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_science_elo","value":1506.8261122633007,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_science_elo_votes","value":5128,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_science_elo_interval","value":8.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_science_elo","value":1506.0221713246235,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_science_elo_votes","value":6883,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_science_elo_interval","value":7.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_science_elo","value":1504.1943596780677,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_science_elo_votes","value":2879,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_science_elo_interval","value":11.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_science_elo","value":1502.6434288544638,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_science_elo_votes","value":606,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_science_elo_interval","value":23.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_science_elo","value":1501.8947089550613,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_science_elo_votes","value":1327,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_science_elo_interval","value":16.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_science_elo","value":1497.1585099556419,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_science_elo_votes","value":21312,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_science_elo_interval","value":5.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_science_elo","value":1494.445618086532,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_science_elo_votes","value":7792,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_science_elo_interval","value":7.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_science_elo","value":1488.41468214299,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_science_elo_votes","value":5824,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_science_elo_interval","value":8.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_science_elo","value":1485.4902801914495,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_science_elo_votes","value":11612,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_science_elo_interval","value":6.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_science_elo","value":1484.5273866349312,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_science_elo_votes","value":7211,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_science_elo_interval","value":7.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_science_elo","value":1482.724779851597,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_science_elo_votes","value":5416,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_science_elo_interval","value":8.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_science_elo","value":1482.1970862671303,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_science_elo_votes","value":12499,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_science_elo_interval","value":6.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_science_elo","value":1480.0530968110143,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_science_elo_votes","value":20874,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_science_elo_interval","value":4.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_science_elo","value":1478.575171398071,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_science_elo_votes","value":1187,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_science_elo_interval","value":17.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_science_elo","value":1478.0812193016206,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_science_elo_votes","value":10648,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_science_elo_interval","value":6.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_science_elo","value":1477.7100170313154,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_science_elo_votes","value":10348,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_science_elo_interval","value":6.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_science_elo","value":1476.9915900412025,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_science_elo_votes","value":10441,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_science_elo_interval","value":6.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_science_elo","value":1474.9287582677532,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_science_elo_votes","value":11651,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_science_elo_interval","value":6.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_science_elo","value":1470.1082713933567,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_science_elo_votes","value":9166,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_science_elo_interval","value":7.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_science_elo","value":1468.0999161987852,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_science_elo_votes","value":6717,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_science_elo_interval","value":7.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_science_elo","value":1467.680577154352,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_science_elo_votes","value":3689,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_science_elo_interval","value":10.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_science_elo","value":1464.6959871461913,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_science_elo_votes","value":6541,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_science_elo_interval","value":7.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_science_elo","value":1464.5842851938319,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_science_elo_votes","value":6771,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_science_elo_interval","value":7.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_science_elo","value":1462.7005603484697,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_science_elo_votes","value":1739,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_science_elo_interval","value":14.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_science_elo","value":1460.4359927506077,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_science_elo_votes","value":4716,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_science_elo_interval","value":8.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_science_elo","value":1459.8630181354126,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_science_elo_votes","value":1929,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_science_elo_interval","value":13.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_science_elo","value":1459.5003330672264,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_science_elo_votes","value":8222,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_science_elo_interval","value":7.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_science_elo","value":1459.4301662834166,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_science_elo_votes","value":6883,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_science_elo_interval","value":7.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_science_elo","value":1457.8552265466187,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_science_elo_votes","value":2142,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_science_elo_interval","value":12.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_science_elo","value":1457.2653438703364,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_science_elo_votes","value":933,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_science_elo_interval","value":18.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_science_elo","value":1456.5488373188439,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_science_elo_votes","value":15315,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_science_elo_interval","value":5.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_science_elo","value":1456.2448973411697,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_science_elo_votes","value":5930,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_science_elo_interval","value":7.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_science_elo","value":1455.6705502233926,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_science_elo_votes","value":6582,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_science_elo_interval","value":7.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_science_elo","value":1455.150281538033,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_science_elo_votes","value":6689,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_science_elo_interval","value":7.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_science_elo","value":1453.6208096422358,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_science_elo_votes","value":11580,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_science_elo_interval","value":6.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_science_elo","value":1453.4523434278747,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_science_elo_votes","value":7099,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_science_elo_interval","value":7.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_science_elo","value":1452.8984430370015,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_science_elo_votes","value":10165,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_science_elo_interval","value":6.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_science_elo","value":1452.583122129116,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_science_elo_votes","value":1156,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_science_elo_interval","value":17.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_science_elo","value":1451.4464182765028,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_science_elo_votes","value":570,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_science_elo_interval","value":24.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_science_elo","value":1451.1487693641484,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_science_elo_votes","value":5856,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_science_elo_interval","value":8.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_science_elo","value":1448.1854658294992,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_science_elo_votes","value":1644,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_science_elo_interval","value":14.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_science_elo","value":1447.6863109232088,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_science_elo_votes","value":13610,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_science_elo_interval","value":5.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_science_elo","value":1446.5100154959769,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_science_elo_votes","value":8412,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_science_elo_interval","value":7.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_science_elo","value":1446.4598401524709,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_science_elo_votes","value":928,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_science_elo_interval","value":18.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_science_elo","value":1445.4659899566086,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_science_elo_votes","value":7632,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_science_elo_interval","value":7.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_science_elo","value":1444.5019301337204,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_science_elo_votes","value":1733,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_science_elo_interval","value":15.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_science_elo","value":1444.2869753232576,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_science_elo_votes","value":1232,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_science_elo_interval","value":16.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_science_elo","value":1444.112918885154,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_science_elo_votes","value":3858,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_science_elo_interval","value":9.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_science_elo","value":1440.1400277294076,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_science_elo_votes","value":7714,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_science_elo_interval","value":7.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_science_elo","value":1438.9787348196357,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_science_elo_votes","value":7649,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_science_elo_interval","value":7.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_science_elo","value":1437.333697735228,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_science_elo_votes","value":15760,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_science_elo_interval","value":5.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_science_elo","value":1437.223734427576,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_science_elo_votes","value":4815,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_science_elo_interval","value":8.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_science_elo","value":1436.6895155703169,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_science_elo_votes","value":4778,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_science_elo_interval","value":8.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_science_elo","value":1434.4786120175584,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_science_elo_votes","value":3531,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_science_elo_interval","value":9.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_science_elo","value":1432.9962429600273,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_science_elo_votes","value":6720,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_science_elo_interval","value":7.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_science_elo","value":1432.8082628696386,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_science_elo_votes","value":20582,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_science_elo_interval","value":4.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_science_elo","value":1432.6572038210047,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_science_elo_votes","value":1495,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_science_elo_interval","value":15.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_science_elo","value":1431.9992038177968,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_science_elo_votes","value":4913,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_science_elo_interval","value":8.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_science_elo","value":1430.242950477087,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_science_elo_votes","value":1939,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_science_elo_interval","value":13.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_science_elo","value":1430.2059251581175,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_science_elo_votes","value":3388,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_science_elo_interval","value":10.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_science_elo","value":1429.3316608584096,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_science_elo_votes","value":9925,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_science_elo_interval","value":6.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_science_elo","value":1428.3673531680915,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_science_elo_votes","value":1940,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_science_elo_interval","value":13.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_science_elo","value":1427.0253862724392,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_science_elo_votes","value":5384,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_science_elo_interval","value":8.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_science_elo","value":1425.4719728311704,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_science_elo_votes","value":10507,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_science_elo_interval","value":6.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_science_elo","value":1425.04588652013,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_science_elo_votes","value":8275,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_science_elo_interval","value":6.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_science_elo","value":1417.2094824105575,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_science_elo_votes","value":10529,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_science_elo_interval","value":6.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_science_elo","value":1416.8997528897482,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_science_elo_votes","value":12270,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_science_elo_interval","value":5.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_science_elo","value":1416.8378811487992,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_science_elo_votes","value":1982,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_science_elo_interval","value":13.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_science_elo","value":1416.6846574731098,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_science_elo_votes","value":13637,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_science_elo_interval","value":5.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_science_elo","value":1416.306897936044,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_science_elo_votes","value":5009,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_science_elo_interval","value":8.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_science_elo","value":1415.5121374265923,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_science_elo_votes","value":9839,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_science_elo_interval","value":6.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_science_elo","value":1414.5112841214388,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_science_elo_votes","value":9818,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_science_elo_interval","value":6.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_science_elo","value":1413.106585523273,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_science_elo_votes","value":5196,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_science_elo_interval","value":8.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_science_elo","value":1406.834598103766,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_science_elo_votes","value":4921,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_science_elo_interval","value":8.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_science_elo","value":1405.8242612328695,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_science_elo_votes","value":24337,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_science_elo_interval","value":4.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_science_elo","value":1403.187224474133,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_science_elo_votes","value":3536,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_science_elo_interval","value":10.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_science_elo","value":1399.3654527698104,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_science_elo_votes","value":11796,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_science_elo_interval","value":6.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_science_elo","value":1392.8533430761418,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_science_elo_votes","value":3678,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_science_elo_interval","value":9.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_science_elo","value":1389.2052283100836,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_science_elo_votes","value":481,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_science_elo_interval","value":26.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_science_elo","value":1387.581597423993,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_science_elo_votes","value":1224,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_science_elo_interval","value":16.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_science_elo","value":1384.2861833594561,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_science_elo_votes","value":2102,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_science_elo_interval","value":12.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_science_elo","value":1382.9989792724139,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_science_elo_votes","value":7867,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_science_elo_interval","value":7.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_science_elo","value":1382.3044656976808,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_science_elo_votes","value":2131,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_science_elo_interval","value":12.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_science_elo","value":1381.8887571478585,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_science_elo_votes","value":8492,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_science_elo_interval","value":6.89,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_science_elo","value":1381.658398029053,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_science_elo_votes","value":7628,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_science_elo_interval","value":7.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_science_elo","value":1381.5696531889187,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_science_elo_votes","value":4830,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_science_elo_interval","value":8.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_science_elo","value":1374.1705982068584,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_science_elo_votes","value":10518,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_science_elo_interval","value":6.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_science_elo","value":1372.1389332005167,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_science_elo_votes","value":798,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_science_elo_interval","value":20.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_science_elo","value":1370.6754778029356,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_science_elo_votes","value":4208,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_science_elo_interval","value":9.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_science_elo","value":1369.099820471398,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_science_elo_votes","value":7139,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_science_elo_interval","value":7.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_science_elo","value":1368.7659005856515,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_science_elo_votes","value":4820,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_science_elo_interval","value":8.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_science_elo","value":1365.8496324027515,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_science_elo_votes","value":760,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_science_elo_interval","value":20.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_science_elo","value":1357.868775555517,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_science_elo_votes","value":1878,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_science_elo_interval","value":13.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_science_elo","value":1355.2346078535304,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_science_elo_votes","value":5098,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_science_elo_interval","value":9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_science_elo","value":1353.7143417727273,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_science_elo_votes","value":5802,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_science_elo_interval","value":7.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_science_elo","value":1353.68839482639,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_science_elo_votes","value":7542,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_science_elo_interval","value":7.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_science_elo","value":1348.3481786625325,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_science_elo_votes","value":1123,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_science_elo_interval","value":17.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_science_elo","value":1347.1230805233388,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_science_elo_votes","value":4026,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_science_elo_interval","value":9.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_science_elo","value":1344.3532315804796,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_science_elo_votes","value":493,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_science_elo_interval","value":25.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_science_elo","value":1339.196451603246,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_science_elo_votes","value":3382,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_science_elo_interval","value":10.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_science_elo","value":1339.1177907517842,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_science_elo_votes","value":9391,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_science_elo_interval","value":6.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_science_elo","value":1334.7063883384697,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_science_elo_votes","value":525,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_science_elo_interval","value":26.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_science_elo","value":1330.1788434244838,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_science_elo_votes","value":735,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_science_elo_interval","value":21.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_science_elo","value":1328.52323063061,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_science_elo_votes","value":6496,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_science_elo_interval","value":7.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_science_elo","value":1321.391053962676,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_science_elo_votes","value":4585,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_science_elo_interval","value":9.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_science_elo","value":1318.660599731831,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_science_elo_votes","value":1307,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_science_elo_interval","value":16.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_science_elo","value":1315.0780043640395,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_science_elo_votes","value":9611,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_science_elo_interval","value":6.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_science_elo","value":1305.5012637996056,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_science_elo_votes","value":780,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_science_elo_interval","value":20.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_science_elo","value":1297.3101831683402,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_science_elo_votes","value":1162,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_science_elo_interval","value":16.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_science_elo","value":1296.0917043423174,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_science_elo_votes","value":1669,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_science_elo_interval","value":14.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_science_elo","value":1294.8284368238792,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_science_elo_votes","value":19017,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_science_elo_interval","value":6.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_science_elo","value":1287.5965004387624,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_science_elo_votes","value":6713,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_science_elo_interval","value":7.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_science_elo","value":1285.945590749352,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_science_elo_votes","value":11641,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_science_elo_interval","value":6.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_science_elo","value":1283.9976742327694,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_science_elo_votes","value":9352,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_science_elo_interval","value":6.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_science_elo","value":1277.942809995294,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_science_elo_votes","value":4979,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_science_elo_interval","value":8.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_science_elo","value":1275.9642650967494,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_science_elo_votes","value":9381,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_science_elo_interval","value":7.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_science_elo","value":1274.826161982524,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_science_elo_votes","value":6932,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_science_elo_interval","value":7.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_science_elo","value":1273.899331642746,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_science_elo_votes","value":7560,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_science_elo_interval","value":8.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_science_elo","value":1266.1557668448195,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_science_elo_votes","value":7485,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_science_elo_interval","value":8.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_science_elo","value":1264.9753172665917,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_science_elo_votes","value":5223,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_science_elo_interval","value":8.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_science_elo","value":1251.7768328806787,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_science_elo_votes","value":1639,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_science_elo_interval","value":14.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_science_elo","value":1234.8316711840594,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_science_elo_votes","value":2579,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_science_elo_interval","value":11.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_science_elo","value":1228.0415848221578,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_science_elo_votes","value":12863,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_science_elo_interval","value":6.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_science_elo","value":1221.3521333562824,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_science_elo_votes","value":956,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_science_elo_interval","value":18.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_science_elo","value":1218.2251943399733,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_science_elo_votes","value":1620,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_science_elo_interval","value":14.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_science_elo","value":1206.4596667633853,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_science_elo_votes","value":4245,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_science_elo_interval","value":9.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_science_elo","value":1193.2203345673172,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_science_elo_votes","value":8403,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_science_elo_interval","value":7.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_science_elo","value":1105.7924819678788,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_science_elo_votes","value":1355,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_science_elo_interval","value":17.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_science_elo","value":1054.5682653701856,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_science_elo_votes","value":1407,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_science_elo_interval","value":17.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_medicine_elo","value":1553.970751460023,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_medicine_elo_votes","value":334,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_medicine_elo_interval","value":32.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_medicine_elo","value":1529.6243016076505,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_medicine_elo_votes","value":1134,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_medicine_elo_interval","value":18.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_medicine_elo","value":1526.2421611596767,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_medicine_elo_votes","value":2458,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_medicine_elo_interval","value":12.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_medicine_elo","value":1513.483587537547,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_medicine_elo_votes","value":564,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_medicine_elo_interval","value":26.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_medicine_elo","value":1507.663063021086,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_medicine_elo_votes","value":227,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_medicine_elo_interval","value":38.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_medicine_elo","value":1507.1519461443515,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_medicine_elo_votes","value":2687,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_medicine_elo_interval","value":12.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_medicine_elo","value":1505.10908413197,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_medicine_elo_votes","value":6131,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_medicine_elo_interval","value":8.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_medicine_elo","value":1501.121186042469,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_medicine_elo_votes","value":1860,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_medicine_elo_interval","value":14.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_medicine_elo","value":1495.3432439381588,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_medicine_elo_votes","value":4959,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_medicine_elo_interval","value":9.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_medicine_elo","value":1492.2220142838178,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_medicine_elo_votes","value":1957,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_medicine_elo_interval","value":14.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_medicine_elo","value":1490.9741928993753,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_medicine_elo_votes","value":254,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_medicine_elo_interval","value":36.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_medicine_elo","value":1488.8477521787763,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_medicine_elo_votes","value":558,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_medicine_elo_interval","value":25.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_medicine_elo","value":1488.1560341948095,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_medicine_elo_votes","value":2230,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_medicine_elo_interval","value":12.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_medicine_elo","value":1487.8457690479145,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_medicine_elo_votes","value":1222,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_medicine_elo_interval","value":17.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_medicine_elo","value":1485.9684285433095,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_medicine_elo_votes","value":9525,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_medicine_elo_interval","value":7.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_medicine_elo","value":1482.8977835117062,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_medicine_elo_votes","value":3559,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_medicine_elo_interval","value":10.6,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_medicine_elo","value":1481.4730639285565,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_medicine_elo_votes","value":2983,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_medicine_elo_interval","value":11.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_medicine_elo","value":1477.0372512986867,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_medicine_elo_votes","value":3145,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_medicine_elo_interval","value":11.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_medicine_elo","value":1475.8543527326513,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_medicine_elo_votes","value":2224,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_medicine_elo_interval","value":13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_medicine_elo","value":1475.787152758573,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_medicine_elo_votes","value":7994,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_medicine_elo_interval","value":7.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_medicine_elo","value":1473.1683964041013,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_medicine_elo_votes","value":5336,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_medicine_elo_interval","value":8.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_medicine_elo","value":1473.0396463573643,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_medicine_elo_votes","value":4478,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_medicine_elo_interval","value":9.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_medicine_elo","value":1468.7123554503455,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_medicine_elo_votes","value":826,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_medicine_elo_interval","value":20.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_medicine_elo","value":1468.0738932269185,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_medicine_elo_votes","value":2557,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_medicine_elo_interval","value":12.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_medicine_elo","value":1465.511305021709,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_medicine_elo_votes","value":4066,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_medicine_elo_interval","value":9.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_medicine_elo","value":1465.437808963067,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_medicine_elo_votes","value":2985,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_medicine_elo_interval","value":11.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_medicine_elo","value":1464.9763223093523,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_medicine_elo_votes","value":5328,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_medicine_elo_interval","value":8.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_medicine_elo","value":1464.26338308496,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_medicine_elo_votes","value":4774,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_medicine_elo_interval","value":9.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_medicine_elo","value":1457.9900162881038,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_medicine_elo_votes","value":4839,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_medicine_elo_interval","value":9.27,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_medicine_elo","value":1456.81446747048,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_medicine_elo_votes","value":2628,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_medicine_elo_interval","value":11.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_medicine_elo","value":1456.555211242726,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_medicine_elo_votes","value":2931,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_medicine_elo_interval","value":11.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_medicine_elo","value":1456.3650682751502,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_medicine_elo_votes","value":509,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_medicine_elo_interval","value":25.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_medicine_elo","value":1455.7686201284357,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_medicine_elo_votes","value":468,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_medicine_elo_interval","value":27.08,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_medicine_elo","value":1455.4090928242674,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_medicine_elo_votes","value":1182,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_medicine_elo_interval","value":17.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_medicine_elo","value":1455.133367893458,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_medicine_elo_votes","value":2136,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_medicine_elo_interval","value":12.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_medicine_elo","value":1455.001170105637,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_medicine_elo_votes","value":1934,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_medicine_elo_interval","value":13.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_medicine_elo","value":1454.6896267987115,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_medicine_elo_votes","value":1385,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_medicine_elo_interval","value":16.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_medicine_elo","value":1454.5811372276223,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_medicine_elo_votes","value":787,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_medicine_elo_interval","value":21.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_medicine_elo","value":1454.2254442340625,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_medicine_elo_votes","value":6965,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_medicine_elo_interval","value":7.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_medicine_elo","value":1451.1179508699302,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_medicine_elo_votes","value":259,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_medicine_elo_interval","value":37.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_medicine_elo","value":1451.0429592949022,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_medicine_elo_votes","value":5437,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_medicine_elo_interval","value":8.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_medicine_elo","value":1450.5637356708573,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_medicine_elo_votes","value":422,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_medicine_elo_interval","value":27.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_medicine_elo","value":1448.0109110795117,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_medicine_elo_votes","value":3681,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_medicine_elo_interval","value":10.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_medicine_elo","value":1447.798486325721,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_medicine_elo_votes","value":2766,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_medicine_elo_interval","value":11.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_medicine_elo","value":1447.3880747806213,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_medicine_elo_votes","value":3325,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_medicine_elo_interval","value":11.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_medicine_elo","value":1445.6151659842842,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_medicine_elo_votes","value":501,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_medicine_elo_interval","value":26.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_medicine_elo","value":1444.992565551884,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_medicine_elo_votes","value":5922,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_medicine_elo_interval","value":7.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_medicine_elo","value":1444.9642647975388,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_medicine_elo_votes","value":1229,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_medicine_elo_interval","value":17.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_medicine_elo","value":1443.6167764466497,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_medicine_elo_votes","value":5391,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_medicine_elo_interval","value":8.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_medicine_elo","value":1443.5936318343176,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_medicine_elo_votes","value":4920,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_medicine_elo_interval","value":8.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_medicine_elo","value":1443.3573008855271,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_medicine_elo_votes","value":3585,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_medicine_elo_interval","value":10.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_medicine_elo","value":1442.1840792321484,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_medicine_elo_votes","value":4321,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_medicine_elo_interval","value":9.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_medicine_elo","value":1442.105813899996,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_medicine_elo_votes","value":3479,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_medicine_elo_interval","value":10.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_medicine_elo","value":1440.7873601066528,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_medicine_elo_votes","value":1511,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_medicine_elo_interval","value":15.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_medicine_elo","value":1440.5304118657443,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_medicine_elo_votes","value":2938,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_medicine_elo_interval","value":11.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_medicine_elo","value":1439.7684569726741,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_medicine_elo_votes","value":3118,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_medicine_elo_interval","value":10.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_medicine_elo","value":1438.489932404466,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_medicine_elo_votes","value":702,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_medicine_elo_interval","value":22.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_medicine_elo","value":1438.1387348920948,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_medicine_elo_votes","value":2610,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_medicine_elo_interval","value":12.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_medicine_elo","value":1432.6748965978495,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_medicine_elo_votes","value":743,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_medicine_elo_interval","value":21.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_medicine_elo","value":1431.9058189431535,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_medicine_elo_votes","value":2922,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_medicine_elo_interval","value":11.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_medicine_elo","value":1431.8401218020533,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_medicine_elo_votes","value":3433,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_medicine_elo_interval","value":10.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_medicine_elo","value":1430.662170206306,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_medicine_elo_votes","value":627,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_medicine_elo_interval","value":24.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_medicine_elo","value":1430.3012633319333,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_medicine_elo_votes","value":3105,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_medicine_elo_interval","value":11.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_medicine_elo","value":1427.889681516204,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_medicine_elo_votes","value":7893,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_medicine_elo_interval","value":7.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_medicine_elo","value":1427.7472344931537,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_medicine_elo_votes","value":4773,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_medicine_elo_interval","value":9.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_medicine_elo","value":1427.640987228453,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_medicine_elo_votes","value":391,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_medicine_elo_interval","value":28.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_medicine_elo","value":1427.4220660505591,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_medicine_elo_votes","value":596,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_medicine_elo_interval","value":23.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_medicine_elo","value":1425.0761679732282,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_medicine_elo_votes","value":2038,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_medicine_elo_interval","value":13.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_medicine_elo","value":1424.6367586081524,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_medicine_elo_votes","value":6179,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_medicine_elo_interval","value":8.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_medicine_elo","value":1423.5326490389746,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_medicine_elo_votes","value":2190,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_medicine_elo_interval","value":12.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_medicine_elo","value":1422.690419750756,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_medicine_elo_votes","value":523,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_medicine_elo_interval","value":25.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_medicine_elo","value":1421.2895014979306,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_medicine_elo_votes","value":2284,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_medicine_elo_interval","value":12.6,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_medicine_elo","value":1420.8650580956203,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_medicine_elo_votes","value":2044,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_medicine_elo_interval","value":13.6,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_medicine_elo","value":1413.077775600833,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_medicine_elo_votes","value":1783,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_medicine_elo_interval","value":14.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_medicine_elo","value":1412.918138057448,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_medicine_elo_votes","value":4432,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_medicine_elo_interval","value":9.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_medicine_elo","value":1411.395651639345,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_medicine_elo_votes","value":2332,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_medicine_elo_interval","value":12.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_medicine_elo","value":1409.141387567452,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_medicine_elo_votes","value":5829,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_medicine_elo_interval","value":8.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_medicine_elo","value":1408.581622757931,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_medicine_elo_votes","value":4241,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_medicine_elo_interval","value":9.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_medicine_elo","value":1408.3417396230013,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_medicine_elo_votes","value":845,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_medicine_elo_interval","value":20.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_medicine_elo","value":1407.5065306591378,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_medicine_elo_votes","value":4388,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_medicine_elo_interval","value":9.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_medicine_elo","value":1401.43514179205,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_medicine_elo_votes","value":1645,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_medicine_elo_interval","value":14.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_medicine_elo","value":1399.291917964813,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_medicine_elo_votes","value":814,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_medicine_elo_interval","value":20.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_medicine_elo","value":1398.8938071679922,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_medicine_elo_votes","value":3041,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_medicine_elo_interval","value":11.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_medicine_elo","value":1394.1400458510066,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_medicine_elo_votes","value":4762,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_medicine_elo_interval","value":9.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_medicine_elo","value":1393.5408260619947,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_medicine_elo_votes","value":10077,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_medicine_elo_interval","value":6.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_medicine_elo","value":1392.338956646911,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_medicine_elo_votes","value":1327,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_medicine_elo_interval","value":16.36,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_medicine_elo","value":1392.047941989672,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_medicine_elo_votes","value":708,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_medicine_elo_interval","value":22.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_medicine_elo","value":1391.0760417512167,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_medicine_elo_votes","value":2342,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_medicine_elo_interval","value":12.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_medicine_elo","value":1389.2595177035957,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_medicine_elo_votes","value":188,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_medicine_elo_interval","value":41.36,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_medicine_elo","value":1387.8684807500304,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_medicine_elo_votes","value":1624,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_medicine_elo_interval","value":14.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_medicine_elo","value":1386.036157481783,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_medicine_elo_votes","value":746,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_medicine_elo_interval","value":21.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_medicine_elo","value":1383.790313696666,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_medicine_elo_votes","value":5323,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_medicine_elo_interval","value":9.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_medicine_elo","value":1383.1441634346693,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_medicine_elo_votes","value":2656,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_medicine_elo_interval","value":11.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_medicine_elo","value":1382.8233446310712,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_medicine_elo_votes","value":512,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_medicine_elo_interval","value":25.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_medicine_elo","value":1379.6129810977566,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_medicine_elo_votes","value":1436,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_medicine_elo_interval","value":15.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_medicine_elo","value":1379.376115639712,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_medicine_elo_votes","value":2773,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_medicine_elo_interval","value":11.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_medicine_elo","value":1371.5221091085436,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_medicine_elo_votes","value":1426,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_medicine_elo_interval","value":16.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_medicine_elo","value":1369.3009956006351,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_medicine_elo_votes","value":4788,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_medicine_elo_interval","value":9.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_medicine_elo","value":1368.2098019773941,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_medicine_elo_votes","value":212,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_medicine_elo_interval","value":38.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_medicine_elo","value":1366.6741406568772,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_medicine_elo_votes","value":315,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_medicine_elo_interval","value":33.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_medicine_elo","value":1363.4575181636794,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_medicine_elo_votes","value":231,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_medicine_elo_interval","value":37.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_medicine_elo","value":1361.3391448742077,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_medicine_elo_votes","value":2491,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_medicine_elo_interval","value":12.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_medicine_elo","value":1357.512654322965,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_medicine_elo_votes","value":3222,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_medicine_elo_interval","value":11.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_medicine_elo","value":1354.869322371597,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_medicine_elo_votes","value":1273,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_medicine_elo_interval","value":17.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_medicine_elo","value":1354.8403099580257,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_medicine_elo_votes","value":2090,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_medicine_elo_interval","value":13.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_medicine_elo","value":1349.7955601808706,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_medicine_elo_votes","value":2287,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_medicine_elo_interval","value":13.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_medicine_elo","value":1349.1538823262815,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_medicine_elo_votes","value":233,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_medicine_elo_interval","value":36.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_medicine_elo","value":1346.5923932735298,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_medicine_elo_votes","value":1487,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_medicine_elo_interval","value":16.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_medicine_elo","value":1343.2087245017,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_medicine_elo_votes","value":840,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_medicine_elo_interval","value":20.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_medicine_elo","value":1341.805904831682,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_medicine_elo_votes","value":197,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_medicine_elo_interval","value":38.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_medicine_elo","value":1335.681552991131,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_medicine_elo_votes","value":470,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_medicine_elo_interval","value":26.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_medicine_elo","value":1334.6645958085887,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_medicine_elo_votes","value":3059,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_medicine_elo_interval","value":11.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_medicine_elo","value":1334.2367083367644,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_medicine_elo_votes","value":237,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_medicine_elo_interval","value":40.08,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_medicine_elo","value":1334.2050380740145,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_medicine_elo_votes","value":155,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_medicine_elo_interval","value":46.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_medicine_elo","value":1330.2004620975845,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_medicine_elo_votes","value":824,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_medicine_elo_interval","value":20.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_medicine_elo","value":1324.4137505884155,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_medicine_elo_votes","value":2311,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_medicine_elo_interval","value":12.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_medicine_elo","value":1317.7969869987728,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_medicine_elo_votes","value":1615,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_medicine_elo_interval","value":14.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_medicine_elo","value":1309.8418147505085,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_medicine_elo_votes","value":564,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_medicine_elo_interval","value":25.27,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_medicine_elo","value":1298.6977211146884,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_medicine_elo_votes","value":3036,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_medicine_elo_interval","value":11.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_medicine_elo","value":1281.673431092664,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_medicine_elo_votes","value":3439,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_medicine_elo_interval","value":11.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_medicine_elo","value":1277.9400633427001,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_medicine_elo_votes","value":5984,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_medicine_elo_interval","value":10.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_medicine_elo","value":1276.1589674271547,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_medicine_elo_votes","value":302,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_medicine_elo_interval","value":32.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_medicine_elo","value":1275.400727569838,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_medicine_elo_votes","value":2293,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_medicine_elo_interval","value":13.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_medicine_elo","value":1275.236234864137,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_medicine_elo_votes","value":2731,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_medicine_elo_interval","value":11.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_medicine_elo","value":1275.054270193828,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_medicine_elo_votes","value":1816,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_medicine_elo_interval","value":14.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_medicine_elo","value":1267.1268604700554,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_medicine_elo_votes","value":1946,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_medicine_elo_interval","value":14.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_medicine_elo","value":1258.3968408842502,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_medicine_elo_votes","value":1956,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_medicine_elo_interval","value":13.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_medicine_elo","value":1257.117169060175,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_medicine_elo_votes","value":2821,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_medicine_elo_interval","value":12.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_medicine_elo","value":1251.7873458180982,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_medicine_elo_votes","value":2174,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_medicine_elo_interval","value":13.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_medicine_elo","value":1245.5679178086582,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_medicine_elo_votes","value":2423,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_medicine_elo_interval","value":13.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_medicine_elo","value":1237.7876778862978,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_medicine_elo_votes","value":547,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_medicine_elo_interval","value":24.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_medicine_elo","value":1215.4458977978554,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_medicine_elo_votes","value":654,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_medicine_elo_interval","value":23.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_medicine_elo","value":1208.2732429535338,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_medicine_elo_votes","value":500,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_medicine_elo_interval","value":25.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_medicine_elo","value":1201.6475848381208,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_medicine_elo_votes","value":1037,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_medicine_elo_interval","value":19.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_medicine_elo","value":1197.6318247894171,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_medicine_elo_votes","value":3862,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_medicine_elo_interval","value":11.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_medicine_elo","value":1186.4524244290847,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_medicine_elo_votes","value":221,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_medicine_elo_interval","value":36.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_medicine_elo","value":1181.5600872613682,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_medicine_elo_votes","value":2564,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_medicine_elo_interval","value":13.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_medicine_elo","value":1104.2542354531565,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_medicine_elo_votes","value":441,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_medicine_elo_interval","value":30,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_medicine_elo","value":1009.080679568528,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_medicine_elo_votes","value":445,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_medicine_elo_interval","value":31.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_legal_elo","value":1548.8765418081252,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_legal_elo_votes","value":402,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_legal_elo_interval","value":30.08,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_legal_elo","value":1529.1068526336362,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_legal_elo_votes","value":2803,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_legal_elo_interval","value":11.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_legal_elo","value":1520.5160138325032,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_legal_elo_votes","value":280,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_legal_elo_interval","value":37.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_legal_elo","value":1518.6847695109132,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_legal_elo_votes","value":632,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_legal_elo_interval","value":23.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_legal_elo","value":1512.419772232584,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_legal_elo_votes","value":6644,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_legal_elo_interval","value":8.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_legal_elo","value":1511.4245348171635,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_legal_elo_votes","value":1201,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_legal_elo_interval","value":17.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_legal_elo","value":1510.211969656062,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_legal_elo_votes","value":712,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_legal_elo_interval","value":23.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_legal_elo","value":1504.8554699555425,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_legal_elo_votes","value":5256,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_legal_elo_interval","value":8.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_legal_elo","value":1502.3927352580376,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_legal_elo_votes","value":2567,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_legal_elo_interval","value":12.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_legal_elo","value":1500.6465035034757,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_legal_elo_votes","value":1500,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_legal_elo_interval","value":15.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_legal_elo","value":1499.4976641760138,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_legal_elo_votes","value":3514,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_legal_elo_interval","value":10.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_legal_elo","value":1498.8065014456558,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_legal_elo_votes","value":3312,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_legal_elo_interval","value":10.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_legal_elo","value":1495.1027871343792,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_legal_elo_votes","value":2302,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_legal_elo_interval","value":12.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_legal_elo","value":1493.0578669582626,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_legal_elo_votes","value":2052,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_legal_elo_interval","value":13.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_legal_elo","value":1490.7390538931486,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_legal_elo_votes","value":5618,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_legal_elo_interval","value":8.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_legal_elo","value":1487.784230629461,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_legal_elo_votes","value":3849,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_legal_elo_interval","value":10.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_legal_elo","value":1486.4958196875755,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_legal_elo_votes","value":10501,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_legal_elo_interval","value":6.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_legal_elo","value":1485.7127254214472,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_legal_elo_votes","value":5239,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_legal_elo_interval","value":8.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_legal_elo","value":1484.9612256695436,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_legal_elo_votes","value":591,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_legal_elo_interval","value":24.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_legal_elo","value":1484.1113882687969,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_legal_elo_votes","value":345,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_legal_elo_interval","value":31.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_legal_elo","value":1480.7937956471028,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_legal_elo_votes","value":3674,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_legal_elo_interval","value":10.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_legal_elo","value":1479.8850240064994,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_legal_elo_votes","value":3027,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_legal_elo_interval","value":11.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_legal_elo","value":1479.6774559378168,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_legal_elo_votes","value":8937,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_legal_elo_interval","value":6.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_legal_elo","value":1476.8036994576544,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_legal_elo_votes","value":5534,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_legal_elo_interval","value":8.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_legal_elo","value":1476.101734182217,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_legal_elo_votes","value":3432,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_legal_elo_interval","value":10.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_legal_elo","value":1473.9580938120478,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_legal_elo_votes","value":2692,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_legal_elo_interval","value":12.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_legal_elo","value":1473.8839392692523,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_legal_elo_votes","value":6151,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_legal_elo_interval","value":8.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_legal_elo","value":1470.114150593822,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_legal_elo_votes","value":5707,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_legal_elo_interval","value":8.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_legal_elo","value":1465.3339247089948,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_legal_elo_votes","value":4966,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_legal_elo_interval","value":8.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_legal_elo","value":1464.1711481913458,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_legal_elo_votes","value":4494,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_legal_elo_interval","value":9.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_legal_elo","value":1463.2735133774756,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_legal_elo_votes","value":3349,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_legal_elo_interval","value":10.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_legal_elo","value":1461.4643535130583,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_legal_elo_votes","value":3695,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_legal_elo_interval","value":10.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_legal_elo","value":1461.2938403436415,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_legal_elo_votes","value":3028,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_legal_elo_interval","value":11.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_legal_elo","value":1459.0196177689572,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_legal_elo_votes","value":5431,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_legal_elo_interval","value":8.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_legal_elo","value":1458.7230274127971,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_legal_elo_votes","value":3065,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_legal_elo_interval","value":10.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_legal_elo","value":1455.9460575815024,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_legal_elo_votes","value":415,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_legal_elo_interval","value":27.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_legal_elo","value":1454.893055585223,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_legal_elo_votes","value":4252,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_legal_elo_interval","value":9.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_legal_elo","value":1452.702611484338,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_legal_elo_votes","value":2269,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_legal_elo_interval","value":12.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_legal_elo","value":1451.9224910518922,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_legal_elo_votes","value":3568,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_legal_elo_interval","value":10.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_legal_elo","value":1450.5441207260806,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_legal_elo_votes","value":5987,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_legal_elo_interval","value":7.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_legal_elo","value":1448.1183639967358,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_legal_elo_votes","value":3363,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_legal_elo_interval","value":10.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_legal_elo","value":1447.9938816266717,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_legal_elo_votes","value":2450,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_legal_elo_interval","value":11.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_legal_elo","value":1446.699717455131,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_legal_elo_votes","value":1799,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_legal_elo_interval","value":14.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_legal_elo","value":1446.0667752202412,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_legal_elo_votes","value":3477,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_legal_elo_interval","value":10.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_legal_elo","value":1444.775466042763,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_legal_elo_votes","value":970,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_legal_elo_interval","value":18.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_legal_elo","value":1441.692407800977,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_legal_elo_votes","value":925,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_legal_elo_interval","value":19.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_legal_elo","value":1440.3625393604286,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_legal_elo_votes","value":7182,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_legal_elo_interval","value":7.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_legal_elo","value":1438.928812902827,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_legal_elo_votes","value":825,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_legal_elo_interval","value":20.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_legal_elo","value":1438.613540071091,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_legal_elo_votes","value":452,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_legal_elo_interval","value":26.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_legal_elo","value":1438.5050410730698,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_legal_elo_votes","value":4148,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_legal_elo_interval","value":9.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_legal_elo","value":1438.344819056766,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_legal_elo_votes","value":736,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_legal_elo_interval","value":22.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_legal_elo","value":1437.9876864167447,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_legal_elo_votes","value":890,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_legal_elo_interval","value":20.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_legal_elo","value":1437.7514072417896,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_legal_elo_votes","value":5214,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_legal_elo_interval","value":8.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_legal_elo","value":1437.5874348186017,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_legal_elo_votes","value":1475,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_legal_elo_interval","value":15.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_legal_elo","value":1436.9628999272652,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_legal_elo_votes","value":3623,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_legal_elo_interval","value":10.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_legal_elo","value":1433.4328984513425,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_legal_elo_votes","value":615,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_legal_elo_interval","value":23.36,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_legal_elo","value":1431.2051425356824,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_legal_elo_votes","value":3060,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_legal_elo_interval","value":11.36,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_legal_elo","value":1430.99422060727,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_legal_elo_votes","value":1414,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_legal_elo_interval","value":15.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_legal_elo","value":1430.817110927592,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_legal_elo_votes","value":1900,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_legal_elo_interval","value":13.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_legal_elo","value":1430.1005391002939,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_legal_elo_votes","value":8909,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_legal_elo_interval","value":6.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_legal_elo","value":1428.3199180593856,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_legal_elo_votes","value":6607,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_legal_elo_interval","value":7.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_legal_elo","value":1427.7994275015203,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_legal_elo_votes","value":3745,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_legal_elo_interval","value":10.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_legal_elo","value":1427.2598371544025,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_legal_elo_votes","value":3769,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_legal_elo_interval","value":9.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_legal_elo","value":1427.0373474159069,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_legal_elo_votes","value":2481,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_legal_elo_interval","value":12.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_legal_elo","value":1424.972219292173,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_legal_elo_votes","value":3491,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_legal_elo_interval","value":10.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_legal_elo","value":1424.7428506523283,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_legal_elo_votes","value":1016,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_legal_elo_interval","value":18.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_legal_elo","value":1424.3668147709334,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_legal_elo_votes","value":3775,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_legal_elo_interval","value":10.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_legal_elo","value":1422.2686112936979,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_legal_elo_votes","value":597,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_legal_elo_interval","value":23.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_legal_elo","value":1422.2311332421814,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_legal_elo_votes","value":2344,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_legal_elo_interval","value":12.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_legal_elo","value":1419.954852396333,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_legal_elo_votes","value":940,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_legal_elo_interval","value":19.6,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_legal_elo","value":1418.4307620940813,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_legal_elo_votes","value":5023,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_legal_elo_interval","value":8.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_legal_elo","value":1418.3839946924293,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_legal_elo_votes","value":1370,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_legal_elo_interval","value":16.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_legal_elo","value":1417.4177637497792,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_legal_elo_votes","value":5338,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_legal_elo_interval","value":8.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_legal_elo","value":1415.776133569565,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_legal_elo_votes","value":2801,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_legal_elo_interval","value":11.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_legal_elo","value":1414.7562307059495,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_legal_elo_votes","value":532,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_legal_elo_interval","value":24.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_legal_elo","value":1414.633499142983,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_legal_elo_votes","value":5073,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_legal_elo_interval","value":9.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_legal_elo","value":1407.8013855141282,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_legal_elo_votes","value":4662,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_legal_elo_interval","value":9.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_legal_elo","value":1407.2767531471022,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_legal_elo_votes","value":263,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_legal_elo_interval","value":35.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_legal_elo","value":1406.3855963857307,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_legal_elo_votes","value":798,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_legal_elo_interval","value":20.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_legal_elo","value":1405.4052939943545,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_legal_elo_votes","value":2192,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_legal_elo_interval","value":12.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_legal_elo","value":1403.3904762902,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_legal_elo_votes","value":6534,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_legal_elo_interval","value":8.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_legal_elo","value":1400.3781534392979,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_legal_elo_votes","value":11207,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_legal_elo_interval","value":6.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_legal_elo","value":1399.1822689228252,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_legal_elo_votes","value":3236,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_legal_elo_interval","value":10.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_legal_elo","value":1398.853469528227,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_legal_elo_votes","value":2384,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_legal_elo_interval","value":12.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_legal_elo","value":1397.4374174548727,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_legal_elo_votes","value":4813,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_legal_elo_interval","value":9.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_legal_elo","value":1394.1056425872323,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_legal_elo_votes","value":212,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_legal_elo_interval","value":39.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_legal_elo","value":1391.2105665564668,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_legal_elo_votes","value":553,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_legal_elo_interval","value":24.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_legal_elo","value":1386.5096017110977,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_legal_elo_votes","value":1463,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_legal_elo_interval","value":15.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_legal_elo","value":1385.5797658973604,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_legal_elo_votes","value":5796,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_legal_elo_interval","value":8.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_legal_elo","value":1381.4122703103264,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_legal_elo_votes","value":1909,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_legal_elo_interval","value":13.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_legal_elo","value":1380.8796651009682,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_legal_elo_votes","value":1781,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_legal_elo_interval","value":14.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_legal_elo","value":1380.5941088294219,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_legal_elo_votes","value":217,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_legal_elo_interval","value":38.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_legal_elo","value":1378.8957961655522,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_legal_elo_votes","value":2905,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_legal_elo_interval","value":11.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_legal_elo","value":1375.0288187617691,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_legal_elo_votes","value":2661,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_legal_elo_interval","value":11.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_legal_elo","value":1374.745455873527,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_legal_elo_votes","value":1693,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_legal_elo_interval","value":14.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_legal_elo","value":1368.0248759758158,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_legal_elo_votes","value":1454,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_legal_elo_interval","value":15.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_legal_elo","value":1367.645864044634,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_legal_elo_votes","value":4975,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_legal_elo_interval","value":9.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_legal_elo","value":1365.7400012440569,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_legal_elo_votes","value":3304,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_legal_elo_interval","value":10.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_legal_elo","value":1363.7961433805926,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_legal_elo_votes","value":840,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_legal_elo_interval","value":20.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_legal_elo","value":1359.0923252407588,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_legal_elo_votes","value":900,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_legal_elo_interval","value":19.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_legal_elo","value":1357.75791695096,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_legal_elo_votes","value":1559,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_legal_elo_interval","value":15.36,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_legal_elo","value":1357.2953852421506,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_legal_elo_votes","value":869,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_legal_elo_interval","value":19.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_legal_elo","value":1354.2016616672931,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_legal_elo_votes","value":1874,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_legal_elo_interval","value":13.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_legal_elo","value":1350.0244107792853,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_legal_elo_votes","value":2748,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_legal_elo_interval","value":11.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_legal_elo","value":1347.6293446288232,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_legal_elo_votes","value":3434,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_legal_elo_interval","value":10.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_legal_elo","value":1347.3753670533008,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_legal_elo_votes","value":432,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_legal_elo_interval","value":27.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_legal_elo","value":1344.9221792061323,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_legal_elo_votes","value":2389,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_legal_elo_interval","value":12.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_legal_elo","value":1342.990815310411,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_legal_elo_votes","value":2437,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_legal_elo_interval","value":12.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_legal_elo","value":1337.6701007564948,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_legal_elo_votes","value":271,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_legal_elo_interval","value":33.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_legal_elo","value":1336.7919780666955,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_legal_elo_votes","value":2337,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_legal_elo_interval","value":12.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_legal_elo","value":1328.2720606070313,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_legal_elo_votes","value":1023,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_legal_elo_interval","value":17.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_legal_elo","value":1326.987571723329,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_legal_elo_votes","value":245,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_legal_elo_interval","value":35.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_legal_elo","value":1326.899614664245,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_legal_elo_votes","value":273,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_legal_elo_interval","value":36.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_legal_elo","value":1324.3807555855515,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_legal_elo_votes","value":285,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_legal_elo_interval","value":32.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_legal_elo","value":1313.8082591865223,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_legal_elo_votes","value":1754,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_legal_elo_interval","value":13.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_legal_elo","value":1313.4910428614571,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_legal_elo_votes","value":6743,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_legal_elo_interval","value":10.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_legal_elo","value":1305.0747675561079,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_legal_elo_votes","value":3866,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_legal_elo_interval","value":10.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_legal_elo","value":1304.7027228707939,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_legal_elo_votes","value":3598,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_legal_elo_interval","value":10.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_legal_elo","value":1299.8178151571738,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_legal_elo_votes","value":382,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_legal_elo_interval","value":28.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_legal_elo","value":1297.4031483600236,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_legal_elo_votes","value":469,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_legal_elo_interval","value":26.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_legal_elo","value":1287.7069945708884,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_legal_elo_votes","value":2386,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_legal_elo_interval","value":12.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_legal_elo","value":1285.6254480405157,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_legal_elo_votes","value":2583,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_legal_elo_interval","value":12.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_legal_elo","value":1284.3545560475584,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_legal_elo_votes","value":1978,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_legal_elo_interval","value":13.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_legal_elo","value":1283.9412562212206,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_legal_elo_votes","value":3153,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_legal_elo_interval","value":10.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_legal_elo","value":1283.2813988841222,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_legal_elo_votes","value":3177,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_legal_elo_interval","value":11.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_legal_elo","value":1279.8113907735958,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_legal_elo_votes","value":678,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_legal_elo_interval","value":23.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_legal_elo","value":1275.8500757487982,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_legal_elo_votes","value":2735,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_legal_elo_interval","value":12.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_legal_elo","value":1275.0233849884091,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_legal_elo_votes","value":2674,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_legal_elo_interval","value":12.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_legal_elo","value":1270.152075811928,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_legal_elo_votes","value":2115,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_legal_elo_interval","value":13.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_legal_elo","value":1268.165007907174,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_legal_elo_votes","value":592,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_legal_elo_interval","value":23.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_legal_elo","value":1256.5060777570357,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_legal_elo_votes","value":273,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_legal_elo_interval","value":34.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_legal_elo","value":1240.955911101368,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_legal_elo_votes","value":4458,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_legal_elo_interval","value":10.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_legal_elo","value":1240.8113168253178,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_legal_elo_votes","value":1341,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_legal_elo_interval","value":16.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_legal_elo","value":1229.4058304350924,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_legal_elo_votes","value":569,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_legal_elo_interval","value":24.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_legal_elo","value":1218.6988014929539,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_legal_elo_votes","value":869,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_legal_elo_interval","value":20.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_legal_elo","value":1206.0780420853746,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_legal_elo_votes","value":2882,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_legal_elo_interval","value":12.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_legal_elo","value":1115.0370627739092,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_legal_elo_votes","value":506,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_legal_elo_interval","value":27.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_legal_elo","value":1070.4589916289221,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_legal_elo_votes","value":489,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_legal_elo_interval","value":29.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_business_elo","value":1525.0648066803526,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_business_elo_votes","value":891,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_business_elo_interval","value":20.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_business_elo","value":1500.5756838972748,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_business_elo_votes","value":6053,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_business_elo_interval","value":8.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_business_elo","value":1497.6422125152185,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_business_elo_votes","value":15952,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_business_elo_interval","value":5.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_business_elo","value":1492.9039253189328,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_business_elo_votes","value":3190,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_business_elo_interval","value":10.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_business_elo","value":1492.6915441258545,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_business_elo_votes","value":2662,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_business_elo_interval","value":11.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_business_elo","value":1492.2485936243966,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_business_elo_votes","value":1479,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_business_elo_interval","value":15.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_business_elo","value":1490.249736867187,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_business_elo_votes","value":13025,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_business_elo_interval","value":6.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_business_elo","value":1481.6283975479275,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_business_elo_votes","value":1496,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_business_elo_interval","value":15.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_business_elo","value":1480.346996297186,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_business_elo_votes","value":8357,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_business_elo_interval","value":7.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_business_elo","value":1479.7885043584154,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_business_elo_votes","value":5159,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_business_elo_interval","value":8.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_business_elo","value":1478.8308214559747,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_business_elo_votes","value":6835,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_business_elo_interval","value":7.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_business_elo","value":1478.1287329711754,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_business_elo_votes","value":13723,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_business_elo_interval","value":6.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_business_elo","value":1478.0508735788878,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_business_elo_votes","value":4953,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_business_elo_interval","value":8.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_business_elo","value":1477.608867056468,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_business_elo_votes","value":560,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_business_elo_interval","value":24.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_business_elo","value":1474.4968050780344,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_business_elo_votes","value":13095,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_business_elo_interval","value":6.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_business_elo","value":1470.5950901657332,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_business_elo_votes","value":8131,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_business_elo_interval","value":7.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_business_elo","value":1469.5649451614506,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_business_elo_votes","value":6158,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_business_elo_interval","value":8.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_business_elo","value":1467.1694708013852,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_business_elo_votes","value":713,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_business_elo_interval","value":22.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_business_elo","value":1466.876555571472,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_business_elo_votes","value":9395,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_business_elo_interval","value":6.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_business_elo","value":1466.5050563082414,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_business_elo_votes","value":14570,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_business_elo_interval","value":5.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_business_elo","value":1464.0701526731036,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_business_elo_votes","value":6836,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_business_elo_interval","value":7.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_business_elo","value":1463.7695619780877,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_business_elo_votes","value":14063,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_business_elo_interval","value":6.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_business_elo","value":1461.3585956602362,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_business_elo_votes","value":6067,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_business_elo_interval","value":8.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_business_elo","value":1459.962973551746,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_business_elo_votes","value":1177,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_business_elo_interval","value":17.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_business_elo","value":1459.8715111014312,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_business_elo_votes","value":24753,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_business_elo_interval","value":4.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_business_elo","value":1457.760826449136,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_business_elo_votes","value":12750,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_business_elo_interval","value":6.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_business_elo","value":1455.9778884011164,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_business_elo_votes","value":7516,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_business_elo_interval","value":7.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_business_elo","value":1455.2806675740346,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_business_elo_votes","value":1999,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_business_elo_interval","value":13.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_business_elo","value":1451.7751478524135,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_business_elo_votes","value":12138,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_business_elo_interval","value":6.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_business_elo","value":1448.3531200667621,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_business_elo_votes","value":14098,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_business_elo_interval","value":5.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_business_elo","value":1446.7099876506527,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_business_elo_votes","value":8036,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_business_elo_interval","value":7.36,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_business_elo","value":1444.6193690758819,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_business_elo_votes","value":7937,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_business_elo_interval","value":7.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_business_elo","value":1443.287856775409,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_business_elo_votes","value":11386,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_business_elo_interval","value":6.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_business_elo","value":1440.8912018955368,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_business_elo_votes","value":7620,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_business_elo_interval","value":7.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_business_elo","value":1440.0859682305468,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_business_elo_votes","value":15836,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_business_elo_interval","value":5.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_business_elo","value":1439.511201152485,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_business_elo_votes","value":22814,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_business_elo_interval","value":4.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_business_elo","value":1439.2248112080113,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_business_elo_votes","value":7568,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_business_elo_interval","value":7.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_business_elo","value":1438.4928155796335,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_business_elo_votes","value":7707,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_business_elo_interval","value":7.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_business_elo","value":1435.9977549665055,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_business_elo_votes","value":1233,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_business_elo_interval","value":16.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_business_elo","value":1435.352144386915,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_business_elo_votes","value":9531,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_business_elo_interval","value":6.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_business_elo","value":1435.278015052022,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_business_elo_votes","value":12339,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_business_elo_interval","value":6.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_business_elo","value":1434.9865484829852,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_business_elo_votes","value":4265,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_business_elo_interval","value":9.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_business_elo","value":1434.902193481588,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_business_elo_votes","value":2142,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_business_elo_interval","value":12.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_business_elo","value":1434.8293504789392,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_business_elo_votes","value":1228,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_business_elo_interval","value":16.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_business_elo","value":1434.7666441816095,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_business_elo_votes","value":8382,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_business_elo_interval","value":7.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_business_elo","value":1434.3325781655997,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_business_elo_votes","value":18675,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_business_elo_interval","value":5.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_business_elo","value":1432.9770474438137,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_business_elo_votes","value":2226,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_business_elo_interval","value":13.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_business_elo","value":1432.0327314457513,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_business_elo_votes","value":9679,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_business_elo_interval","value":7.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_business_elo","value":1431.1350985981837,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_business_elo_votes","value":7739,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_business_elo_interval","value":7.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_business_elo","value":1430.5967979002492,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_business_elo_votes","value":1180,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_business_elo_interval","value":16.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_business_elo","value":1430.017988004897,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_business_elo_votes","value":10076,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_business_elo_interval","value":6.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_business_elo","value":1429.8752703086786,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_business_elo_votes","value":5900,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_business_elo_interval","value":7.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_business_elo","value":1429.2609418650577,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_business_elo_votes","value":2293,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_business_elo_interval","value":12.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_business_elo","value":1429.2202110953756,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_business_elo_votes","value":1115,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_business_elo_interval","value":16.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_business_elo","value":1426.2461647838804,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_business_elo_votes","value":2257,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_business_elo_interval","value":12.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_business_elo","value":1425.0215307702306,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_business_elo_votes","value":10441,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_business_elo_interval","value":6.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_business_elo","value":1422.9073627856892,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_business_elo_votes","value":2302,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_business_elo_interval","value":12.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_business_elo","value":1421.9152768693295,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_business_elo_votes","value":6602,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_business_elo_interval","value":7.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_business_elo","value":1421.882051708568,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_business_elo_votes","value":4287,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_business_elo_interval","value":9.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_business_elo","value":1420.003506044543,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_business_elo_votes","value":4226,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_business_elo_interval","value":9.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_business_elo","value":1418.0584395520984,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_business_elo_votes","value":18259,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_business_elo_interval","value":4.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_business_elo","value":1417.7336045692928,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_business_elo_votes","value":12859,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_business_elo_interval","value":6.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_business_elo","value":1416.2206476950291,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_business_elo_votes","value":6902,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_business_elo_interval","value":7.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_business_elo","value":1416.065529519944,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_business_elo_votes","value":5368,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_business_elo_interval","value":8.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_business_elo","value":1414.1471649797952,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_business_elo_votes","value":5731,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_business_elo_interval","value":8.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_business_elo","value":1414.040462790751,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_business_elo_votes","value":9758,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_business_elo_interval","value":6.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_business_elo","value":1412.6132699823165,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_business_elo_votes","value":6001,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_business_elo_interval","value":8.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_business_elo","value":1412.4820312428653,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_business_elo_votes","value":1527,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_business_elo_interval","value":15.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_business_elo","value":1412.1041257886802,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_business_elo_votes","value":2250,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_business_elo_interval","value":12.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_business_elo","value":1409.9076780408607,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_business_elo_votes","value":9052,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_business_elo_interval","value":6.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_business_elo","value":1407.4553940908627,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_business_elo_votes","value":16427,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_business_elo_interval","value":5.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_business_elo","value":1405.6516775684627,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_business_elo_votes","value":14066,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_business_elo_interval","value":5.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_business_elo","value":1403.5202752185023,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_business_elo_votes","value":22747,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_business_elo_interval","value":4.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_business_elo","value":1401.5376455120304,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_business_elo_votes","value":2852,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_business_elo_interval","value":11.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_business_elo","value":1400.3727058847055,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_business_elo_votes","value":28782,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_business_elo_interval","value":4.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_business_elo","value":1399.5670271200008,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_business_elo_votes","value":5586,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_business_elo_interval","value":8.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_business_elo","value":1398.5724453977457,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_business_elo_votes","value":5610,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_business_elo_interval","value":8.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_business_elo","value":1394.517820287228,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_business_elo_votes","value":12205,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_business_elo_interval","value":6.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_business_elo","value":1394.0239886809538,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_business_elo_votes","value":11840,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_business_elo_interval","value":6.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_business_elo","value":1393.5780827327374,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_business_elo_votes","value":6113,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_business_elo_interval","value":7.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_business_elo","value":1392.6496379115085,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_business_elo_votes","value":9485,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_business_elo_interval","value":6.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_business_elo","value":1389.298200076539,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_business_elo_votes","value":12561,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_business_elo_interval","value":6.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_business_elo","value":1389.1843318559113,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_business_elo_votes","value":4119,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_business_elo_interval","value":9.36,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_business_elo","value":1388.8378114548466,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_business_elo_votes","value":1996,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_business_elo_interval","value":13.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_business_elo","value":1387.444338260194,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_business_elo_votes","value":718,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_business_elo_interval","value":21.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_business_elo","value":1381.1860987044324,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_business_elo_votes","value":14233,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_business_elo_interval","value":6.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_business_elo","value":1380.9203397826718,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_business_elo_votes","value":3872,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_business_elo_interval","value":9.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_business_elo","value":1376.4192412811135,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_business_elo_votes","value":364,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_business_elo_interval","value":29.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_business_elo","value":1370.4194305965875,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_business_elo_votes","value":5503,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_business_elo_interval","value":8.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_business_elo","value":1369.0482520159946,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_business_elo_votes","value":8237,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_business_elo_interval","value":7.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_business_elo","value":1368.2958385784937,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_business_elo_votes","value":2312,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_business_elo_interval","value":12.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_business_elo","value":1366.1598414726914,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_business_elo_votes","value":12592,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_business_elo_interval","value":6.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_business_elo","value":1363.7048061647579,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_business_elo_votes","value":1455,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_business_elo_interval","value":14.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_business_elo","value":1359.9494323226431,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_business_elo_votes","value":2490,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_business_elo_interval","value":11.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_business_elo","value":1359.5128426650026,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_business_elo_votes","value":6495,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_business_elo_interval","value":7.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_business_elo","value":1359.46719927096,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_business_elo_votes","value":553,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_business_elo_interval","value":24.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_business_elo","value":1358.90298294426,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_business_elo_votes","value":5361,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_business_elo_interval","value":8.36,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_business_elo","value":1357.8333273675823,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_business_elo_votes","value":4833,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_business_elo_interval","value":8.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_business_elo","value":1356.364020118122,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_business_elo_votes","value":8383,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_business_elo_interval","value":7.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_business_elo","value":1349.4966125402532,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_business_elo_votes","value":512,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_business_elo_interval","value":24.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_business_elo","value":1349.1776828644931,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_business_elo_votes","value":6855,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_business_elo_interval","value":7.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_business_elo","value":1343.2803958352424,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_business_elo_votes","value":4381,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_business_elo_interval","value":9.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_business_elo","value":1342.7817791695402,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_business_elo_votes","value":2244,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_business_elo_interval","value":12.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_business_elo","value":1335.8201923751458,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_business_elo_votes","value":1324,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_business_elo_interval","value":16.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_business_elo","value":1329.3834379107857,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_business_elo_votes","value":6124,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_business_elo_interval","value":8.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_business_elo","value":1327.5760384600485,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_business_elo_votes","value":2720,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_business_elo_interval","value":11.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_business_elo","value":1324.9148956031083,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_business_elo_votes","value":7033,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_business_elo_interval","value":7.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_business_elo","value":1322.0101713345991,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_business_elo_votes","value":606,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_business_elo_interval","value":24.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_business_elo","value":1321.6600155807605,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_business_elo_votes","value":6009,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_business_elo_interval","value":8.08,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_business_elo","value":1318.801473464645,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_business_elo_votes","value":6017,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_business_elo_interval","value":7.89,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_business_elo","value":1318.262757176682,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_business_elo_votes","value":437,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_business_elo_interval","value":26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_business_elo","value":1314.6796512271794,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_business_elo_votes","value":8787,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_business_elo_interval","value":6.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_business_elo","value":1312.9409342897602,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_business_elo_votes","value":1815,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_business_elo_interval","value":13.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_business_elo","value":1310.9536928564266,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_business_elo_votes","value":390,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_business_elo_interval","value":30.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_business_elo","value":1310.9186469171163,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_business_elo_votes","value":1521,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_business_elo_interval","value":15.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_business_elo","value":1309.0556596709293,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_business_elo_votes","value":906,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_business_elo_interval","value":19.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_business_elo","value":1308.6026763789382,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_business_elo_votes","value":3996,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_business_elo_interval","value":9.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_business_elo","value":1289.3090599408179,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_business_elo_votes","value":7679,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_business_elo_interval","value":7.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_business_elo","value":1283.6693174290535,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_business_elo_votes","value":1835,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_business_elo_interval","value":14.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_business_elo","value":1266.5799310635875,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_business_elo_votes","value":651,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_business_elo_interval","value":21.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_business_elo","value":1264.8541675340625,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_business_elo_votes","value":7765,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_business_elo_interval","value":7.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_business_elo","value":1261.542272490232,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_business_elo_votes","value":13299,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_business_elo_interval","value":7.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_business_elo","value":1260.592470751149,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_business_elo_votes","value":6128,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_business_elo_interval","value":8.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_business_elo","value":1257.4434366660125,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_business_elo_votes","value":5507,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_business_elo_interval","value":8.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_business_elo","value":1256.7730047382377,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_business_elo_votes","value":4922,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_business_elo_interval","value":9.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_business_elo","value":1252.8447572855764,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_business_elo_votes","value":4656,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_business_elo_interval","value":9.27,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_business_elo","value":1242.8471642333338,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_business_elo_votes","value":6629,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_business_elo_interval","value":7.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_business_elo","value":1235.0446654984735,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_business_elo_votes","value":6381,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_business_elo_interval","value":8.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_business_elo","value":1231.7170900865322,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_business_elo_votes","value":5095,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_business_elo_interval","value":9.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_business_elo","value":1225.9443124030868,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_business_elo_votes","value":5167,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_business_elo_interval","value":9.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_business_elo","value":1223.871724019833,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_business_elo_votes","value":629,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_business_elo_interval","value":21.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_business_elo","value":1215.1040898113806,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_business_elo_votes","value":1132,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_business_elo_interval","value":17.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_business_elo","value":1207.612440000719,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_business_elo_votes","value":8733,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_business_elo_interval","value":7.6,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_business_elo","value":1205.3584809522947,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_business_elo_votes","value":1443,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_business_elo_interval","value":15.6,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_business_elo","value":1198.7172716127016,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_business_elo_votes","value":2438,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_business_elo_interval","value":12.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_business_elo","value":1165.942028854387,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_business_elo_votes","value":5722,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_business_elo_interval","value":8.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_business_elo","value":1157.0999258338259,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_business_elo_votes","value":1152,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_business_elo_interval","value":17.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_business_elo","value":1073.637398638805,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_business_elo_votes","value":1012,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_business_elo_interval","value":19.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_business_elo","value":999.6259394264259,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_business_elo_votes","value":1044,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_business_elo_interval","value":20.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_writing_elo","value":1534.1392664823388,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_writing_elo_votes","value":2477,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_writing_elo_interval","value":13.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_writing_elo","value":1529.0979499765745,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_writing_elo_votes","value":1365,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_writing_elo_interval","value":16.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_writing_elo","value":1508.7167181098798,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_writing_elo_votes","value":4150,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_writing_elo_interval","value":10.08,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_writing_elo","value":1502.675477409784,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_writing_elo_votes","value":21041,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_writing_elo_interval","value":5.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_writing_elo","value":1500.9078646472813,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_writing_elo_votes","value":11803,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_writing_elo_interval","value":6.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_writing_elo","value":1497.5299238802736,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_writing_elo_votes","value":9383,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_writing_elo_interval","value":7.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_writing_elo","value":1495.7009549736408,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_writing_elo_votes","value":10501,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_writing_elo_interval","value":7.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_writing_elo","value":1492.5508597433763,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_writing_elo_votes","value":16572,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_writing_elo_interval","value":6.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_writing_elo","value":1491.2711028571598,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_writing_elo_votes","value":7589,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_writing_elo_interval","value":7.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_writing_elo","value":1491.1898100323006,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_writing_elo_votes","value":948,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_writing_elo_interval","value":19.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_writing_elo","value":1480.8441529996535,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_writing_elo_votes","value":32660,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_writing_elo_interval","value":4.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_writing_elo","value":1478.0599749004523,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_writing_elo_votes","value":7253,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_writing_elo_interval","value":7.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_writing_elo","value":1477.7874517144446,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_writing_elo_votes","value":12654,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_writing_elo_interval","value":6.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_writing_elo","value":1472.036330293829,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_writing_elo_votes","value":1902,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_writing_elo_interval","value":14.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_writing_elo","value":1470.3640817333608,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_writing_elo_votes","value":8723,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_writing_elo_interval","value":7.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_writing_elo","value":1469.7093962875247,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_writing_elo_votes","value":9852,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_writing_elo_interval","value":7.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_writing_elo","value":1468.7315282869554,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_writing_elo_votes","value":1003,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_writing_elo_interval","value":18.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_writing_elo","value":1467.7558846377224,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_writing_elo_votes","value":4941,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_writing_elo_interval","value":9.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_writing_elo","value":1466.0812295411392,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_writing_elo_votes","value":18181,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_writing_elo_interval","value":5.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_writing_elo","value":1462.6084046923165,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_writing_elo_votes","value":10968,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_writing_elo_interval","value":6.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_writing_elo","value":1460.9462643104794,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_writing_elo_votes","value":17290,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_writing_elo_interval","value":5.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_writing_elo","value":1457.8943084942553,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_writing_elo_votes","value":2286,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_writing_elo_interval","value":13.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_writing_elo","value":1457.745000451558,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_writing_elo_votes","value":16350,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_writing_elo_interval","value":5.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_writing_elo","value":1454.5876249920498,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_writing_elo_votes","value":9070,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_writing_elo_interval","value":7.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_writing_elo","value":1454.1551389755332,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_writing_elo_votes","value":16617,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_writing_elo_interval","value":5.6,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_writing_elo","value":1453.8024513639448,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_writing_elo_votes","value":28272,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_writing_elo_interval","value":4.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_writing_elo","value":1451.661442576586,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_writing_elo_votes","value":19549,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_writing_elo_interval","value":5.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_writing_elo","value":1451.3452659405039,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_writing_elo_votes","value":16912,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_writing_elo_interval","value":5.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_writing_elo","value":1447.4838412048653,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_writing_elo_votes","value":11803,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_writing_elo_interval","value":6.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_writing_elo","value":1446.9644465260635,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_writing_elo_votes","value":14140,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_writing_elo_interval","value":6.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_writing_elo","value":1444.9563480261668,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_writing_elo_votes","value":10904,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_writing_elo_interval","value":6.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_writing_elo","value":1443.618487280366,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_writing_elo_votes","value":17602,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_writing_elo_interval","value":5.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_writing_elo","value":1441.8406905601419,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_writing_elo_votes","value":19003,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_writing_elo_interval","value":5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_writing_elo","value":1438.9449913858753,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_writing_elo_votes","value":9584,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_writing_elo_interval","value":7.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_writing_elo","value":1437.7272165544996,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_writing_elo_votes","value":10852,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_writing_elo_interval","value":6.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_writing_elo","value":1436.3210254977002,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_writing_elo_votes","value":7022,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_writing_elo_interval","value":7.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_writing_elo","value":1435.5623087528834,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_writing_elo_votes","value":13577,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_writing_elo_interval","value":6.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_writing_elo","value":1431.2319821234678,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_writing_elo_votes","value":11998,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_writing_elo_interval","value":6.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_writing_elo","value":1431.111461429418,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_writing_elo_votes","value":1429,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_writing_elo_interval","value":15.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_writing_elo","value":1428.6793100917944,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_writing_elo_votes","value":8265,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_writing_elo_interval","value":7.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_writing_elo","value":1427.8522083078992,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_writing_elo_votes","value":9361,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_writing_elo_interval","value":6.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_writing_elo","value":1426.9949769551877,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_writing_elo_votes","value":9785,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_writing_elo_interval","value":7.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_writing_elo","value":1425.4386436380842,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_writing_elo_votes","value":2804,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_writing_elo_interval","value":11.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_writing_elo","value":1423.0236114488744,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_writing_elo_votes","value":1935,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_writing_elo_interval","value":13.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_writing_elo","value":1420.4788733140886,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_writing_elo_votes","value":2759,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_writing_elo_interval","value":11.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_writing_elo","value":1419.6774744147992,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_writing_elo_votes","value":16321,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_writing_elo_interval","value":5.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_writing_elo","value":1419.1949825666065,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_writing_elo_votes","value":11298,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_writing_elo_interval","value":6.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_writing_elo","value":1418.3455418369708,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_writing_elo_votes","value":11246,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_writing_elo_interval","value":6.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_writing_elo","value":1418.0496470570015,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_writing_elo_votes","value":17469,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_writing_elo_interval","value":5.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_writing_elo","value":1415.4077416975133,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_writing_elo_votes","value":8091,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_writing_elo_interval","value":6.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_writing_elo","value":1415.1781215388087,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_writing_elo_votes","value":23093,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_writing_elo_interval","value":4.89,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_writing_elo","value":1414.1214507245395,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_writing_elo_votes","value":3247,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_writing_elo_interval","value":10.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_writing_elo","value":1410.7365528104501,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_writing_elo_votes","value":2827,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_writing_elo_interval","value":10.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_writing_elo","value":1409.8661057249278,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_writing_elo_votes","value":12604,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_writing_elo_interval","value":6.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_writing_elo","value":1409.292504608522,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_writing_elo_votes","value":11536,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_writing_elo_interval","value":6.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_writing_elo","value":1408.1361322400007,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_writing_elo_votes","value":15610,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_writing_elo_interval","value":5.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_writing_elo","value":1407.8474439268402,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_writing_elo_votes","value":791,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_writing_elo_interval","value":20.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_writing_elo","value":1407.5213250478014,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_writing_elo_votes","value":2663,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_writing_elo_interval","value":11.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_writing_elo","value":1406.9383676072143,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_writing_elo_votes","value":10687,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_writing_elo_interval","value":6.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_writing_elo","value":1406.3769358762324,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_writing_elo_votes","value":6078,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_writing_elo_interval","value":8.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_writing_elo","value":1405.6046690846788,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_writing_elo_votes","value":1395,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_writing_elo_interval","value":15.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_writing_elo","value":1405.3681624871024,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_writing_elo_votes","value":28446,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_writing_elo_interval","value":4.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_writing_elo","value":1403.1665976930594,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_writing_elo_votes","value":11160,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_writing_elo_interval","value":6.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_writing_elo","value":1402.4570444850679,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_writing_elo_votes","value":5301,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_writing_elo_interval","value":8.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_writing_elo","value":1401.5719808398608,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_writing_elo_votes","value":4199,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_writing_elo_interval","value":9.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_writing_elo","value":1394.782053097626,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_writing_elo_votes","value":3233,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_writing_elo_interval","value":11.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_writing_elo","value":1392.7595561631351,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_writing_elo_votes","value":15847,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_writing_elo_interval","value":5.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_writing_elo","value":1392.6957104082571,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_writing_elo_votes","value":2353,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_writing_elo_interval","value":12.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_writing_elo","value":1391.7610112906632,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_writing_elo_votes","value":11510,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_writing_elo_interval","value":6.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_writing_elo","value":1390.0646159308344,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_writing_elo_votes","value":22136,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_writing_elo_interval","value":4.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_writing_elo","value":1387.7029741581077,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_writing_elo_votes","value":1860,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_writing_elo_interval","value":13.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_writing_elo","value":1386.8066605836011,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_writing_elo_votes","value":6795,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_writing_elo_interval","value":7.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_writing_elo","value":1386.6860184506227,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_writing_elo_votes","value":36448,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_writing_elo_interval","value":4.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_writing_elo","value":1384.7501446653246,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_writing_elo_votes","value":18665,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_writing_elo_interval","value":5.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_writing_elo","value":1384.372587375985,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_writing_elo_votes","value":2988,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_writing_elo_interval","value":11.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_writing_elo","value":1384.3007815418055,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_writing_elo_votes","value":6777,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_writing_elo_interval","value":7.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_writing_elo","value":1383.1755523383003,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_writing_elo_votes","value":2139,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_writing_elo_interval","value":13.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_writing_elo","value":1380.406564879162,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_writing_elo_votes","value":6497,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_writing_elo_interval","value":7.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_writing_elo","value":1376.036824454141,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_writing_elo_votes","value":20686,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_writing_elo_interval","value":5.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_writing_elo","value":1371.7563165880492,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_writing_elo_votes","value":14800,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_writing_elo_interval","value":5.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_writing_elo","value":1371.441209078158,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_writing_elo_votes","value":13240,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_writing_elo_interval","value":5.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_writing_elo","value":1371.1739557141018,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_writing_elo_votes","value":11339,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_writing_elo_interval","value":6.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_writing_elo","value":1368.843844560718,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_writing_elo_votes","value":14664,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_writing_elo_interval","value":5.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_writing_elo","value":1365.2163340372404,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_writing_elo_votes","value":7053,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_writing_elo_interval","value":7.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_writing_elo","value":1364.7414932597326,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_writing_elo_votes","value":10285,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_writing_elo_interval","value":6.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_writing_elo","value":1360.025461578411,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_writing_elo_votes","value":7663,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_writing_elo_interval","value":7.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_writing_elo","value":1355.2819067390546,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_writing_elo_votes","value":9076,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_writing_elo_interval","value":7.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_writing_elo","value":1354.8086061371075,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_writing_elo_votes","value":5063,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_writing_elo_interval","value":8.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_writing_elo","value":1354.178711413832,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_writing_elo_votes","value":6987,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_writing_elo_interval","value":7.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_writing_elo","value":1347.309953698943,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_writing_elo_votes","value":10592,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_writing_elo_interval","value":6.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_writing_elo","value":1346.6515531275395,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_writing_elo_votes","value":626,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_writing_elo_interval","value":23.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_writing_elo","value":1345.2068510423217,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_writing_elo_votes","value":10072,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_writing_elo_interval","value":6.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_writing_elo","value":1344.227446501397,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_writing_elo_votes","value":6141,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_writing_elo_interval","value":7.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_writing_elo","value":1341.2187250405832,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_writing_elo_votes","value":5948,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_writing_elo_interval","value":8.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_writing_elo","value":1339.73215705333,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_writing_elo_votes","value":5329,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_writing_elo_interval","value":8.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_writing_elo","value":1337.8759264710318,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_writing_elo_votes","value":15395,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_writing_elo_interval","value":6.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_writing_elo","value":1335.9457244544624,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_writing_elo_votes","value":5074,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_writing_elo_interval","value":8.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_writing_elo","value":1331.5393731538788,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_writing_elo_votes","value":1726,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_writing_elo_interval","value":13.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_writing_elo","value":1330.3679235308548,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_writing_elo_votes","value":3064,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_writing_elo_interval","value":10.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_writing_elo","value":1327.6214440480485,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_writing_elo_votes","value":12801,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_writing_elo_interval","value":5.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_writing_elo","value":1319.5474099655305,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_writing_elo_votes","value":2663,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_writing_elo_interval","value":11.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_writing_elo","value":1318.5873309953563,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_writing_elo_votes","value":8635,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_writing_elo_interval","value":6.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_writing_elo","value":1317.70086984203,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_writing_elo_votes","value":2807,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_writing_elo_interval","value":11.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_writing_elo","value":1316.8739704658597,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_writing_elo_votes","value":7280,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_writing_elo_interval","value":7.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_writing_elo","value":1315.5282008803774,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_writing_elo_votes","value":10012,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_writing_elo_interval","value":6.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_writing_elo","value":1313.2047534522549,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_writing_elo_votes","value":4762,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_writing_elo_interval","value":8.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_writing_elo","value":1310.5580718979045,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_writing_elo_votes","value":7705,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_writing_elo_interval","value":7.08,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_writing_elo","value":1307.0769053138347,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_writing_elo_votes","value":1010,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_writing_elo_interval","value":17.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_writing_elo","value":1305.5914615165507,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_writing_elo_votes","value":6642,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_writing_elo_interval","value":7.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_writing_elo","value":1302.4492803621492,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_writing_elo_votes","value":741,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_writing_elo_interval","value":21.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_writing_elo","value":1301.9811086601492,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_writing_elo_votes","value":1071,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_writing_elo_interval","value":17.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_writing_elo","value":1298.2876008255373,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_writing_elo_votes","value":1121,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_writing_elo_interval","value":16.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_writing_elo","value":1297.7461395695552,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_writing_elo_votes","value":29959,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_writing_elo_interval","value":5.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_writing_elo","value":1294.6551360046,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_writing_elo_votes","value":1483,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_writing_elo_interval","value":15.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_writing_elo","value":1294.6440621627735,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_writing_elo_votes","value":13414,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_writing_elo_interval","value":5.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_writing_elo","value":1290.4026656270257,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_writing_elo_votes","value":5939,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_writing_elo_interval","value":7.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_writing_elo","value":1289.6574532333489,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_writing_elo_votes","value":12147,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_writing_elo_interval","value":6.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_writing_elo","value":1288.0759043453381,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_writing_elo_votes","value":1080,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_writing_elo_interval","value":16.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_writing_elo","value":1283.2496220430253,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_writing_elo_votes","value":1727,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_writing_elo_interval","value":14.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_writing_elo","value":1281.9632037066528,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_writing_elo_votes","value":18532,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_writing_elo_interval","value":5.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_writing_elo","value":1277.3691919322239,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_writing_elo_votes","value":8730,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_writing_elo_interval","value":6.89,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_writing_elo","value":1269.93114257467,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_writing_elo_votes","value":837,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_writing_elo_interval","value":22.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_writing_elo","value":1268.5905512546572,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_writing_elo_votes","value":6706,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_writing_elo_interval","value":7.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_writing_elo","value":1268.5211442886502,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_writing_elo_votes","value":7059,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_writing_elo_interval","value":7.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_writing_elo","value":1260.8882105644566,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_writing_elo_votes","value":1583,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_writing_elo_interval","value":14.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_writing_elo","value":1257.8726437527775,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_writing_elo_votes","value":12224,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_writing_elo_interval","value":6.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_writing_elo","value":1254.9799070892425,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_writing_elo_votes","value":13808,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_writing_elo_interval","value":5.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_writing_elo","value":1248.7202631859077,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_writing_elo_votes","value":20390,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_writing_elo_interval","value":5.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_writing_elo","value":1246.908057896027,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_writing_elo_votes","value":10827,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_writing_elo_interval","value":6.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_writing_elo","value":1241.0513899022035,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_writing_elo_votes","value":2672,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_writing_elo_interval","value":11.27,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_writing_elo","value":1238.2573548941705,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_writing_elo_votes","value":2171,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_writing_elo_interval","value":13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_writing_elo","value":1235.7068767635783,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_writing_elo_votes","value":14962,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_writing_elo_interval","value":6.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_writing_elo","value":1213.932258912636,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_writing_elo_votes","value":3942,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_writing_elo_interval","value":9.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_writing_elo","value":1197.8697699945128,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_writing_elo_votes","value":6470,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_writing_elo_interval","value":7.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_writing_elo","value":1193.063611786865,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_writing_elo_votes","value":2597,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_writing_elo_interval","value":11.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_writing_elo","value":1191.0561826627286,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_writing_elo_votes","value":1540,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_writing_elo_interval","value":14.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_writing_elo","value":1162.0668464535188,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_writing_elo_votes","value":13505,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_writing_elo_interval","value":6.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_writing_elo","value":1095.5677925845434,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_writing_elo_votes","value":2118,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_writing_elo_interval","value":13.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_writing_elo","value":1029.7426994298976,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_writing_elo_votes","value":2047,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_writing_elo_interval","value":14.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_media_elo","value":1525.7763571031956,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_media_elo_votes","value":1233,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_text_media_elo_interval","value":18.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_media_elo","value":1510.715012325335,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_media_elo_votes","value":2212,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_text_media_elo_interval","value":13.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_media_elo","value":1495.1565109436667,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_media_elo_votes","value":3666,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_text_media_elo_interval","value":10.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_media_elo","value":1492.003209862965,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_media_elo_votes","value":18420,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_text_media_elo_interval","value":5.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_media_elo","value":1482.1889660052082,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_media_elo_votes","value":10958,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_text_media_elo_interval","value":6.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_media_elo","value":1480.195669144401,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_media_elo_votes","value":9844,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_text_media_elo_interval","value":7.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_media_elo","value":1479.7277834977056,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_media_elo_votes","value":8667,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_text_media_elo_interval","value":7.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_media_elo","value":1478.5853439706875,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_media_elo_votes","value":7249,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_text_media_elo_interval","value":8.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_media_elo","value":1474.1760943220338,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_media_elo_votes","value":15118,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_text_media_elo_interval","value":6.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_media_elo","value":1472.3626827461912,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_media_elo_votes","value":858,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_text_media_elo_interval","value":20.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_media_elo","value":1465.857863175977,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_media_elo_votes","value":29563,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_text_media_elo_interval","value":4.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_media_elo","value":1464.6009395078493,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_media_elo_votes","value":928,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_text_media_elo_interval","value":19.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_media_elo","value":1464.5660189469413,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_media_elo_votes","value":6908,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_text_media_elo_interval","value":7.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_media_elo","value":1459.1308982806222,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_media_elo_votes","value":12062,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_text_media_elo_interval","value":6.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_media_elo","value":1457.5924820556825,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_media_elo_votes","value":1741,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_text_media_elo_interval","value":14.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_media_elo","value":1455.7989821655237,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_media_elo_votes","value":9313,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_text_media_elo_interval","value":7.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_media_elo","value":1455.3033693934217,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_media_elo_votes","value":4509,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_text_media_elo_interval","value":9.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_media_elo","value":1452.3142049728413,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_media_elo_votes","value":8062,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_text_media_elo_interval","value":7.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_media_elo","value":1450.1541943585307,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_media_elo_votes","value":10300,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_text_media_elo_interval","value":7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_media_elo","value":1448.753863436508,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_media_elo_votes","value":16720,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_text_media_elo_interval","value":6.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_media_elo","value":1446.1199280463295,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_media_elo_votes","value":2101,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_text_media_elo_interval","value":13.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_media_elo","value":1442.6035849681832,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_media_elo_votes","value":14929,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_text_media_elo_interval","value":5.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_media_elo","value":1441.0896818219755,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_media_elo_votes","value":23329,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_text_media_elo_interval","value":4.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_media_elo","value":1440.7668975829868,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_media_elo_votes","value":8287,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_text_media_elo_interval","value":7.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_media_elo","value":1440.6441108968502,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_media_elo_votes","value":16188,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_text_media_elo_interval","value":6.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_media_elo","value":1437.9588241306296,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_media_elo_votes","value":10912,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_text_media_elo_interval","value":6.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_media_elo","value":1437.9435941934826,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_media_elo_votes","value":17550,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_text_media_elo_interval","value":5.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_media_elo","value":1437.8010201282952,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_media_elo_votes","value":14154,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_text_media_elo_interval","value":6.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_media_elo","value":1434.0955984536295,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_media_elo_votes","value":14080,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_text_media_elo_interval","value":5.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_media_elo","value":1433.7792056584146,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_media_elo_votes","value":10395,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_text_media_elo_interval","value":6.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_media_elo","value":1430.7137690190932,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_media_elo_votes","value":15933,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_text_media_elo_interval","value":6,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_media_elo","value":1430.4554844605761,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_media_elo_votes","value":12801,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_text_media_elo_interval","value":6.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_media_elo","value":1428.3925367035993,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_media_elo_votes","value":15781,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_text_media_elo_interval","value":5.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_media_elo","value":1427.947728535115,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_media_elo_votes","value":8287,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_text_media_elo_interval","value":7.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_media_elo","value":1425.369861664245,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_media_elo_votes","value":5903,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_text_media_elo_interval","value":8.08,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_media_elo","value":1422.2990551648384,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_media_elo_votes","value":10017,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_text_media_elo_interval","value":6.89,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_media_elo","value":1421.4296289716121,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_media_elo_votes","value":7591,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_text_media_elo_interval","value":7.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_media_elo","value":1418.0685983110254,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_media_elo_votes","value":11055,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_text_media_elo_interval","value":6.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_media_elo","value":1414.4976492116366,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_media_elo_votes","value":7585,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_text_media_elo_interval","value":7.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_media_elo","value":1413.7598698357067,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_media_elo_votes","value":9265,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_text_media_elo_interval","value":7.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_media_elo","value":1413.5285077429376,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_media_elo_votes","value":2550,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_text_media_elo_interval","value":12.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_media_elo","value":1411.038028977859,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_media_elo_votes","value":12785,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_text_media_elo_interval","value":6.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_media_elo","value":1409.7229839264946,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_media_elo_votes","value":1795,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_text_media_elo_interval","value":14.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_media_elo","value":1408.5546019147173,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_media_elo_votes","value":6679,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_text_media_elo_interval","value":7.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_media_elo","value":1407.563356321267,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_media_elo_votes","value":2570,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_text_media_elo_interval","value":12.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_media_elo","value":1407.257953712589,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_media_elo_votes","value":2184,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_text_media_elo_interval","value":12.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_media_elo","value":1404.3705179001124,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_media_elo_votes","value":4315,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5","source":"arena","metric":"arena_text_media_elo_interval","value":9.08,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_media_elo","value":1404.0977254804902,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_media_elo_votes","value":1095,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_text_media_elo_interval","value":17.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_media_elo","value":1403.6013414321312,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_media_elo_votes","value":1111,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_text_media_elo_interval","value":17.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_media_elo","value":1402.845442475958,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_media_elo_votes","value":15034,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_text_media_elo_interval","value":6.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_media_elo","value":1402.2966011053709,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_media_elo_votes","value":10150,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_text_media_elo_interval","value":7.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_media_elo","value":1401.7400903215344,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_media_elo_votes","value":10794,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_text_media_elo_interval","value":6.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_media_elo","value":1401.0301911072127,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_media_elo_votes","value":2426,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_text_media_elo_interval","value":11.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_media_elo","value":1400.3947010728102,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_media_elo_votes","value":3182,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-r1-0528","source":"arena","metric":"arena_text_media_elo_interval","value":10.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_media_elo","value":1399.6755733264438,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_media_elo_votes","value":11211,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_text_media_elo_interval","value":6.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_media_elo","value":1399.5059329923345,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_media_elo_votes","value":10455,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_text_media_elo_interval","value":7.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_media_elo","value":1398.415726006398,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_media_elo_votes","value":14236,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_text_media_elo_interval","value":5.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_media_elo","value":1398.1548966862024,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_media_elo_votes","value":3012,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_text_media_elo_interval","value":11.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_media_elo","value":1398.1490589342018,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_media_elo_votes","value":21199,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_text_media_elo_interval","value":5.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_media_elo","value":1394.647320482446,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_media_elo_votes","value":8785,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_text_media_elo_interval","value":6.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_media_elo","value":1394.6400652904283,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_media_elo_votes","value":5740,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_text_media_elo_interval","value":8.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_media_elo","value":1393.4111829371902,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_media_elo_votes","value":23191,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_text_media_elo_interval","value":4.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_media_elo","value":1392.5774706377047,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_media_elo_votes","value":10607,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_text_media_elo_interval","value":6.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_media_elo","value":1385.714814994522,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_media_elo_votes","value":13681,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_text_media_elo_interval","value":6.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_media_elo","value":1382.5324690573668,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_media_elo_votes","value":627,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"arena","metric":"arena_text_media_elo_interval","value":23.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_media_elo","value":1382.1381221046915,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_media_elo_votes","value":2681,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_text_media_elo_interval","value":11.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_media_elo","value":1380.3540866234277,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_media_elo_votes","value":2948,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_text_media_elo_interval","value":11.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_media_elo","value":1378.8867138334995,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_media_elo_votes","value":5876,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_text_media_elo_interval","value":8.08,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_media_elo","value":1378.370389024715,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_media_elo_votes","value":17744,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_text_media_elo_interval","value":5.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_media_elo","value":1376.2063762060893,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_media_elo_votes","value":1960,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_text_media_elo_interval","value":14.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_media_elo","value":1374.165826579499,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_media_elo_votes","value":18057,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"arena","metric":"arena_text_media_elo_interval","value":4.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_media_elo","value":1373.0482392560166,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_media_elo_votes","value":13900,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_text_media_elo_interval","value":6.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_media_elo","value":1372.6935550212825,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_media_elo_votes","value":10508,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3","source":"arena","metric":"arena_text_media_elo_interval","value":6.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_media_elo","value":1370.7301862582403,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_media_elo_votes","value":17244,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_text_media_elo_interval","value":5.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_media_elo","value":1369.9630255769046,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_media_elo_votes","value":1528,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"arena","metric":"arena_text_media_elo_interval","value":14.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_media_elo","value":1369.3618711346971,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_media_elo_votes","value":32219,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_text_media_elo_interval","value":4.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_media_elo","value":1368.2241835407615,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_media_elo_votes","value":1889,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_text_media_elo_interval","value":14.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_media_elo","value":1365.5278315856795,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_media_elo_votes","value":5750,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_text_media_elo_interval","value":8.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_media_elo","value":1364.7796906137762,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_media_elo_votes","value":9014,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_text_media_elo_interval","value":6.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_media_elo","value":1363.0124350494173,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_media_elo_votes","value":5387,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_text_media_elo_interval","value":8.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_media_elo","value":1360.527827244603,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_media_elo_votes","value":18736,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_text_media_elo_interval","value":5.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_media_elo","value":1359.793675422196,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_media_elo_votes","value":12077,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"stepfun/step-3.5-flash","source":"arena","metric":"arena_text_media_elo_interval","value":6.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_media_elo","value":1358.070066180348,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_media_elo_votes","value":5210,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o1","source":"arena","metric":"arena_text_media_elo_interval","value":8.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_media_elo","value":1356.8556223528133,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_media_elo_votes","value":8019,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"deepseek/deepseek-chat-v3-0324","source":"arena","metric":"arena_text_media_elo_interval","value":6.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_media_elo","value":1350.9266246126633,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_media_elo_votes","value":8419,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_text_media_elo_interval","value":7.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_media_elo","value":1348.946082460405,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_media_elo_votes","value":4225,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-instruct","source":"arena","metric":"arena_text_media_elo_interval","value":9.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_media_elo","value":1347.2761978728618,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_media_elo_votes","value":5953,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_text_media_elo_interval","value":8.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_media_elo","value":1347.0063367340422,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_media_elo_votes","value":12642,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_text_media_elo_interval","value":6.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_media_elo","value":1343.5044625539972,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_media_elo_votes","value":521,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_text_media_elo_interval","value":25.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_media_elo","value":1339.941538397131,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_media_elo_votes","value":4844,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_text_media_elo_interval","value":8.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_media_elo","value":1339.496703693491,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_media_elo_votes","value":5697,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5-air","source":"arena","metric":"arena_text_media_elo_interval","value":7.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_media_elo","value":1336.6521013584868,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_media_elo_votes","value":1263,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"nvidia/nemotron-3-super-120b-a12b","source":"arena","metric":"arena_text_media_elo_interval","value":16.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_media_elo","value":1334.5543875898175,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_media_elo_votes","value":4127,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b-instruct-2507","source":"arena","metric":"arena_text_media_elo_interval","value":9.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_media_elo","value":1330.6812951396757,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_media_elo_votes","value":5524,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_text_media_elo_interval","value":8.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_media_elo","value":1328.5816300068198,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_media_elo_votes","value":8401,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_text_media_elo_interval","value":7.08,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_media_elo","value":1324.476495741104,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_media_elo_votes","value":13668,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_text_media_elo_interval","value":6.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_media_elo","value":1320.0734454733079,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_media_elo_votes","value":8004,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_text_media_elo_interval","value":6.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_media_elo","value":1317.1850335738384,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_media_elo_votes","value":4498,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_text_media_elo_interval","value":9.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_media_elo","value":1315.0174923549807,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_media_elo_votes","value":694,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_text_media_elo_interval","value":21.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_media_elo","value":1312.4595567066044,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_media_elo_votes","value":2445,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-next-80b-a3b-thinking","source":"arena","metric":"arena_text_media_elo_interval","value":11.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_media_elo","value":1308.5826800310367,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_media_elo_votes","value":2252,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"amazon/nova-2-lite-v1","source":"arena","metric":"arena_text_media_elo_interval","value":12.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_media_elo","value":1307.9050205255842,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_media_elo_votes","value":7983,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_text_media_elo_interval","value":7.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_media_elo","value":1306.512820277835,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_media_elo_votes","value":10058,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-a","source":"arena","metric":"arena_text_media_elo_interval","value":6.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_media_elo","value":1303.7875992851364,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_media_elo_votes","value":2138,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.7-flash","source":"arena","metric":"arena_text_media_elo_interval","value":12.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_media_elo","value":1303.2596047792065,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_media_elo_votes","value":6254,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m1","source":"arena","metric":"arena_text_media_elo_interval","value":7.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_media_elo","value":1303.0477022679356,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_media_elo_votes","value":865,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_text_media_elo_interval","value":18.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_media_elo","value":1300.0410813320775,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_media_elo_votes","value":6734,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_text_media_elo_interval","value":7.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_media_elo","value":1297.6210018997913,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_media_elo_votes","value":1192,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_text_media_elo_interval","value":16.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_media_elo","value":1297.5017120697203,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_media_elo_votes","value":697,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-12b-it","source":"arena","metric":"arena_text_media_elo_interval","value":20.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_media_elo","value":1295.6848327410244,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_media_elo_votes","value":6258,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_text_media_elo_interval","value":8.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_media_elo","value":1292.4890791800913,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_media_elo_votes","value":5492,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-120b","source":"arena","metric":"arena_text_media_elo_interval","value":8.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_media_elo","value":1289.4511326399515,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_media_elo_votes","value":17607,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_text_media_elo_interval","value":6.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_media_elo","value":1283.5373264111904,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_media_elo_votes","value":3214,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini-high","source":"arena","metric":"arena_text_media_elo_interval","value":10.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_media_elo","value":1278.832537124754,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_media_elo_votes","value":704,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-32b","source":"arena","metric":"arena_text_media_elo_interval","value":20.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_media_elo","value":1272.6224769710702,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_media_elo_votes","value":10244,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/o3-mini","source":"arena","metric":"arena_text_media_elo_interval","value":6.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_media_elo","value":1272.6189705508978,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_media_elo_votes","value":815,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"ibm-granite/granite-4.2-8b","source":"arena","metric":"arena_text_media_elo_interval","value":22.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_media_elo","value":1268.565215298785,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_media_elo_votes","value":1357,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_text_media_elo_interval","value":16.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_media_elo","value":1267.4351298114732,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_media_elo_votes","value":7043,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_text_media_elo_interval","value":8.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_media_elo","value":1258.1972892263188,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_media_elo_votes","value":4549,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen3-30b-a3b","source":"arena","metric":"arena_text_media_elo_interval","value":8.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_media_elo","value":1253.2220045993263,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_media_elo_votes","value":11284,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_text_media_elo_interval","value":6.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_media_elo","value":1250.1092968173746,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_media_elo_votes","value":5819,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_text_media_elo_interval","value":8.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_media_elo","value":1249.895086327723,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_media_elo_votes","value":6927,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_text_media_elo_interval","value":7.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_media_elo","value":1242.6806944351792,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_media_elo_votes","value":1061,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_text_media_elo_interval","value":17.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_media_elo","value":1242.0789052084504,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_media_elo_votes","value":5278,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_text_media_elo_interval","value":8.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_media_elo","value":1241.5441162147488,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_media_elo_votes","value":7002,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-large-2407","source":"arena","metric":"arena_text_media_elo_interval","value":8.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_media_elo","value":1240.6456535217908,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_media_elo_votes","value":9715,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.3-70b-instruct","source":"arena","metric":"arena_text_media_elo_interval","value":6.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_media_elo","value":1232.778148190917,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_media_elo_votes","value":761,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-3-4b-it","source":"arena","metric":"arena_text_media_elo_interval","value":20.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_media_elo","value":1229.8270377383355,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_media_elo_votes","value":8719,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-70b-instruct","source":"arena","metric":"arena_text_media_elo_interval","value":7.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_media_elo","value":1223.3646134380058,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_media_elo_votes","value":1450,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-plus-08-2024","source":"arena","metric":"arena_text_media_elo_interval","value":14.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_media_elo","value":1216.3873859191058,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_media_elo_votes","value":1730,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"openai/gpt-oss-20b","source":"arena","metric":"arena_text_media_elo_interval","value":14.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_media_elo","value":1212.4715823762663,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_media_elo_votes","value":12280,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"google/gemma-2-27b-it","source":"arena","metric":"arena_text_media_elo_interval","value":6.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_media_elo","value":1210.994779047741,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_media_elo_votes","value":6207,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-72b-instruct","source":"arena","metric":"arena_text_media_elo_interval","value":8.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_media_elo","value":1183.85164487351,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_media_elo_votes","value":2680,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"mistralai/mistral-small-24b-instruct-2501","source":"arena","metric":"arena_text_media_elo_interval","value":11.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_media_elo","value":1161.9639516599775,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_media_elo_votes","value":1593,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"cohere/command-r-08-2024","source":"arena","metric":"arena_text_media_elo_interval","value":14.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_media_elo","value":1161.9272848536505,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_media_elo_votes","value":4486,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"microsoft/phi-4","source":"arena","metric":"arena_text_media_elo_interval","value":9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_media_elo","value":1150.1861386861103,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_media_elo_votes","value":929,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"qwen/qwen-2.5-coder-32b-instruct","source":"arena","metric":"arena_text_media_elo_interval","value":18.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_media_elo","value":1144.6132480666338,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_media_elo_votes","value":7706,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.1-8b-instruct","source":"arena","metric":"arena_text_media_elo_interval","value":7.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_media_elo","value":1083.3978174280805,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_media_elo_votes","value":1149,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-3b-instruct","source":"arena","metric":"arena_text_media_elo_interval","value":17.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_media_elo","value":1025.0864392785118,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_media_elo_votes","value":1151,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"meta-llama/llama-3.2-1b-instruct","source":"arena","metric":"arena_text_media_elo_interval","value":18.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_webdev_react_elo","value":1854.9557498210756,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_webdev_react_elo_votes","value":2007,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_webdev_react_elo_interval","value":17.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_webdev_react_elo","value":1816.8252601047184,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_webdev_react_elo_votes","value":2175,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_webdev_react_elo_interval","value":16.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-astra","source":"arena","metric":"arena_webdev_react_elo","value":1798.1762281523315,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-astra","source":"arena","metric":"arena_webdev_react_elo_votes","value":3665,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-astra","source":"arena","metric":"arena_webdev_react_elo_interval","value":12.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_webdev_react_elo","value":1792.482753715904,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_webdev_react_elo_votes","value":5178,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_webdev_react_elo_interval","value":11.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6.1-sol","source":"arena","metric":"arena_webdev_react_elo","value":1754.047353720869,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6.1-sol","source":"arena","metric":"arena_webdev_react_elo_votes","value":1939,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6.1-sol","source":"arena","metric":"arena_webdev_react_elo_interval","value":16.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_webdev_react_elo","value":1711.1601508752997,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_webdev_react_elo_votes","value":12036,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_webdev_react_elo_interval","value":7.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_webdev_react_elo","value":1692.0861758101214,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_webdev_react_elo_votes","value":8977,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_webdev_react_elo_interval","value":8.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_webdev_react_elo","value":1691.9994404424124,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_webdev_react_elo_votes","value":1043,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_webdev_react_elo_interval","value":20.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-sol","source":"arena","metric":"arena_webdev_react_elo","value":1685.2566972013929,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-sol","source":"arena","metric":"arena_webdev_react_elo_votes","value":2719,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-sol","source":"arena","metric":"arena_webdev_react_elo_interval","value":13.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_webdev_react_elo","value":1672.482739736242,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_webdev_react_elo_votes","value":6046,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_webdev_react_elo_interval","value":9.27,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_webdev_react_elo","value":1670.4628932528235,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_webdev_react_elo_votes","value":12988,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_webdev_react_elo_interval","value":7.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"arena","metric":"arena_webdev_react_elo","value":1666.679694717695,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"arena","metric":"arena_webdev_react_elo_votes","value":1255,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"arena","metric":"arena_webdev_react_elo_interval","value":18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_webdev_react_elo","value":1663.3052722123525,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_webdev_react_elo_votes","value":3212,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_webdev_react_elo_interval","value":11.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"tencent/hy4-preview","source":"arena","metric":"arena_webdev_react_elo","value":1652.7625569230158,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"tencent/hy4-preview","source":"arena","metric":"arena_webdev_react_elo_votes","value":3082,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"tencent/hy4-preview","source":"arena","metric":"arena_webdev_react_elo_interval","value":11.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_webdev_react_elo","value":1648.198775641567,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_webdev_react_elo_votes","value":3333,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_webdev_react_elo_interval","value":11.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_webdev_react_elo","value":1641.2671266574953,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_webdev_react_elo_votes","value":1454,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_webdev_react_elo_interval","value":17.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.3","source":"arena","metric":"arena_webdev_react_elo","value":1641.0596074687783,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.3","source":"arena","metric":"arena_webdev_react_elo_votes","value":6344,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.3","source":"arena","metric":"arena_webdev_react_elo_interval","value":9.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_webdev_react_elo","value":1639.0238212209424,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_webdev_react_elo_votes","value":3201,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_webdev_react_elo_interval","value":11.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_webdev_react_elo","value":1630.9457630661482,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_webdev_react_elo_votes","value":11075,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_webdev_react_elo_interval","value":7.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_webdev_react_elo","value":1630.5471824509536,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_webdev_react_elo_votes","value":6746,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_webdev_react_elo_interval","value":8.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"arena","metric":"arena_webdev_react_elo","value":1628.4736628645387,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"arena","metric":"arena_webdev_react_elo_votes","value":2162,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"arena","metric":"arena_webdev_react_elo_interval","value":13.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_webdev_react_elo","value":1624.3147082925798,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_webdev_react_elo_votes","value":11613,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_webdev_react_elo_interval","value":7.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_webdev_react_elo","value":1619.8364927357147,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_webdev_react_elo_votes","value":11375,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_webdev_react_elo_interval","value":6.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.2","source":"arena","metric":"arena_webdev_react_elo","value":1617.1107508670134,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.2","source":"arena","metric":"arena_webdev_react_elo_votes","value":11346,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.2","source":"arena","metric":"arena_webdev_react_elo_interval","value":7.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-haiku-5.5","source":"arena","metric":"arena_webdev_react_elo","value":1604.7648624369513,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-haiku-5.5","source":"arena","metric":"arena_webdev_react_elo_votes","value":2203,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-haiku-5.5","source":"arena","metric":"arena_webdev_react_elo_interval","value":13.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_webdev_react_elo","value":1601.524668317485,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_webdev_react_elo_votes","value":10463,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_webdev_react_elo_interval","value":7.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"arena","metric":"arena_webdev_react_elo","value":1588.099402399057,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"arena","metric":"arena_webdev_react_elo_votes","value":3099,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"arena","metric":"arena_webdev_react_elo_interval","value":11.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_webdev_react_elo","value":1586.9989648550982,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_webdev_react_elo_votes","value":8109,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_webdev_react_elo_interval","value":8.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_webdev_react_elo","value":1584.878984775523,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_webdev_react_elo_votes","value":3369,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_webdev_react_elo_interval","value":11.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_webdev_react_elo","value":1582.8744799915103,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_webdev_react_elo_votes","value":3019,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_webdev_react_elo_interval","value":11.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_webdev_react_elo","value":1577.097644037401,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_webdev_react_elo_votes","value":6947,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_webdev_react_elo_interval","value":8.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-luna","source":"arena","metric":"arena_webdev_react_elo","value":1573.2874807558069,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-luna","source":"arena","metric":"arena_webdev_react_elo_votes","value":13375,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-luna","source":"arena","metric":"arena_webdev_react_elo_interval","value":7.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_webdev_react_elo","value":1560.4042887874934,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_webdev_react_elo_votes","value":13873,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_webdev_react_elo_interval","value":6.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_webdev_react_elo","value":1558.5623009735104,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_webdev_react_elo_votes","value":1783,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_webdev_react_elo_interval","value":15.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_webdev_react_elo","value":1556.834194772072,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_webdev_react_elo_votes","value":11873,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_webdev_react_elo_interval","value":6.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_webdev_react_elo","value":1555.9242976290243,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_webdev_react_elo_votes","value":7531,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_webdev_react_elo_interval","value":7.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_webdev_react_elo","value":1541.0598564775642,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_webdev_react_elo_votes","value":10721,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_webdev_react_elo_interval","value":6.89,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_webdev_react_elo","value":1538.9706642373094,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_webdev_react_elo_votes","value":15128,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_webdev_react_elo_interval","value":6.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_webdev_react_elo","value":1532.0983046006245,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_webdev_react_elo_votes","value":5371,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_webdev_react_elo_interval","value":9.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-open","source":"arena","metric":"arena_webdev_react_elo","value":1529.267060862955,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-open","source":"arena","metric":"arena_webdev_react_elo_votes","value":864,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-open","source":"arena","metric":"arena_webdev_react_elo_interval","value":21.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_webdev_react_elo","value":1527.5626100485538,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_webdev_react_elo_votes","value":5500,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_webdev_react_elo_interval","value":9.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_webdev_react_elo","value":1525.840458992503,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_webdev_react_elo_votes","value":1487,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_webdev_react_elo_interval","value":16.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.7-max","source":"arena","metric":"arena_webdev_react_elo","value":1513.738725540803,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.7-max","source":"arena","metric":"arena_webdev_react_elo_votes","value":6693,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.7-max","source":"arena","metric":"arena_webdev_react_elo_interval","value":8.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_webdev_react_elo","value":1512.7103454290232,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_webdev_react_elo_votes","value":8787,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_webdev_react_elo_interval","value":7.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_webdev_react_elo","value":1512.4391958877368,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_webdev_react_elo_votes","value":18106,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_webdev_react_elo_interval","value":5.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_webdev_react_elo","value":1510.8298957990887,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_webdev_react_elo_votes","value":3947,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_webdev_react_elo_interval","value":10.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_webdev_react_elo","value":1507.6247747582488,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_webdev_react_elo_votes","value":7697,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_webdev_react_elo_interval","value":7.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_webdev_react_elo","value":1505.830362702627,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_webdev_react_elo_votes","value":12062,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_webdev_react_elo_interval","value":6.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_webdev_react_elo","value":1505.1107048728231,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_webdev_react_elo_votes","value":7329,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_webdev_react_elo_interval","value":8.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_webdev_react_elo","value":1504.8065548057994,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_webdev_react_elo_votes","value":8155,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_webdev_react_elo_interval","value":7.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_webdev_react_elo","value":1495.0161705716014,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_webdev_react_elo_votes","value":6781,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_webdev_react_elo_interval","value":8.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_webdev_react_elo","value":1478.1418964349218,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_webdev_react_elo_votes","value":4740,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_webdev_react_elo_interval","value":10.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_webdev_react_elo","value":1478.080969793338,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_webdev_react_elo_votes","value":13888,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_webdev_react_elo_interval","value":6.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.7-code","source":"arena","metric":"arena_webdev_react_elo","value":1474.9933307807555,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.7-code","source":"arena","metric":"arena_webdev_react_elo_votes","value":3956,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.7-code","source":"arena","metric":"arena_webdev_react_elo_interval","value":10.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_webdev_react_elo","value":1469.3335287732784,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_webdev_react_elo_votes","value":16427,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_webdev_react_elo_interval","value":5.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_webdev_react_elo","value":1453.7882966306581,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_webdev_react_elo_votes","value":13768,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_webdev_react_elo_interval","value":6.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_webdev_react_elo","value":1453.6541133922515,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_webdev_react_elo_votes","value":1234,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_webdev_react_elo_interval","value":19.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"reflection/beam-1.0-501b-a23b","source":"arena","metric":"arena_webdev_react_elo","value":1442.5114604885202,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"reflection/beam-1.0-501b-a23b","source":"arena","metric":"arena_webdev_react_elo_votes","value":1850,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"reflection/beam-1.0-501b-a23b","source":"arena","metric":"arena_webdev_react_elo_interval","value":16.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_webdev_react_elo","value":1440.6480853372093,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_webdev_react_elo_votes","value":9622,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_webdev_react_elo_interval","value":7.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_webdev_react_elo","value":1438.2650319254394,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_webdev_react_elo_votes","value":18253,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_webdev_react_elo_interval","value":5.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_webdev_react_elo","value":1429.0611958976392,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_webdev_react_elo_votes","value":16155,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_webdev_react_elo_interval","value":5.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_webdev_react_elo","value":1424.9336647711675,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_webdev_react_elo_votes","value":11491,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_webdev_react_elo_interval","value":6.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_webdev_react_elo","value":1424.2402991869642,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_webdev_react_elo_votes","value":6529,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_webdev_react_elo_interval","value":8.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_webdev_react_elo","value":1419.8209592469373,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_webdev_react_elo_votes","value":106,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_webdev_react_elo_interval","value":67.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_webdev_react_elo","value":1407.6653600575246,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_webdev_react_elo_votes","value":147,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_webdev_react_elo_interval","value":52.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_webdev_react_elo","value":1403.7643705677874,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_webdev_react_elo_votes","value":10477,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_webdev_react_elo_interval","value":7.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_webdev_react_elo","value":1399.2766151170085,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_webdev_react_elo_votes","value":3554,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_webdev_react_elo_interval","value":11.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.3-codex","source":"arena","metric":"arena_webdev_react_elo","value":1394.8899856109388,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.3-codex","source":"arena","metric":"arena_webdev_react_elo_votes","value":2352,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.3-codex","source":"arena","metric":"arena_webdev_react_elo_interval","value":14.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_webdev_react_elo","value":1387.7929693354345,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_webdev_react_elo_votes","value":12618,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_webdev_react_elo_interval","value":6.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_webdev_react_elo","value":1387.6398857598383,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_webdev_react_elo_votes","value":16758,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_webdev_react_elo_interval","value":5.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_webdev_react_elo","value":1386.4190006698514,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_webdev_react_elo_votes","value":9821,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_webdev_react_elo_interval","value":7.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_webdev_react_elo","value":1386.3265426982116,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_webdev_react_elo_votes","value":1725,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_webdev_react_elo_interval","value":15.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_webdev_react_elo","value":1385.795370945335,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_webdev_react_elo_votes","value":4166,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_webdev_react_elo_interval","value":10.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_webdev_react_elo","value":1373.897129730384,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_webdev_react_elo_votes","value":6619,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_webdev_react_elo_interval","value":8.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_webdev_react_elo","value":1363.225118448057,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_webdev_react_elo_votes","value":2953,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_webdev_react_elo_interval","value":13.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_webdev_react_elo","value":1359.3744714773247,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_webdev_react_elo_votes","value":11333,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_webdev_react_elo_interval","value":6.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_webdev_react_elo","value":1353.2738126179138,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_webdev_react_elo_votes","value":11475,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_webdev_react_elo_interval","value":6.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_webdev_react_elo","value":1352.5370405417243,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_webdev_react_elo_votes","value":7150,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_webdev_react_elo_interval","value":8.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_webdev_react_elo","value":1350.8832655306528,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_webdev_react_elo_votes","value":1290,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_webdev_react_elo_interval","value":18.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_webdev_react_elo","value":1349.6829539474327,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_webdev_react_elo_votes","value":3629,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_webdev_react_elo_interval","value":11.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"tencent/hy3-preview","source":"arena","metric":"arena_webdev_react_elo","value":1348.741664436785,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"tencent/hy3-preview","source":"arena","metric":"arena_webdev_react_elo_votes","value":1216,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"tencent/hy3-preview","source":"arena","metric":"arena_webdev_react_elo_interval","value":19.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_webdev_react_elo","value":1346.1141658569081,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_webdev_react_elo_votes","value":6757,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_webdev_react_elo_interval","value":8.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.2-codex","source":"arena","metric":"arena_webdev_react_elo","value":1329.3444189073916,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.2-codex","source":"arena","metric":"arena_webdev_react_elo_votes","value":4355,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.2-codex","source":"arena","metric":"arena_webdev_react_elo_interval","value":10.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_webdev_react_elo","value":1326.213149311633,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_webdev_react_elo_votes","value":16000,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_webdev_react_elo_interval","value":5.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_webdev_react_elo","value":1306.608641543044,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_webdev_react_elo_votes","value":2628,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_webdev_react_elo_interval","value":13.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_webdev_react_elo","value":1257.4521122185095,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_webdev_react_elo_votes","value":4125,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_webdev_react_elo_interval","value":11.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_webdev_react_elo","value":1254.0650237797686,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_webdev_react_elo_votes","value":1972,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_webdev_react_elo_interval","value":16.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_webdev_react_elo","value":1245.0260877361277,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_webdev_react_elo_votes","value":12326,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_webdev_react_elo_interval","value":7.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_webdev_react_elo","value":1238.0287525950034,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_webdev_react_elo_votes","value":1424,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_webdev_react_elo_interval","value":18.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_webdev_react_elo","value":1230.672217590979,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_webdev_react_elo_votes","value":1157,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_webdev_react_elo_interval","value":21.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_webdev_react_elo","value":1229.1903868956479,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_webdev_react_elo_votes","value":1204,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_webdev_react_elo_interval","value":20.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_webdev_react_elo","value":1159.6813568960602,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_webdev_react_elo_votes","value":845,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_webdev_react_elo_interval","value":26.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6.1-sol","source":"arena","metric":"arena_webdev_html_elo","value":1799.8552391186015,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6.1-sol","source":"arena","metric":"arena_webdev_html_elo_votes","value":510,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6.1-sol","source":"arena","metric":"arena_webdev_html_elo_interval","value":32.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-astra","source":"arena","metric":"arena_webdev_html_elo","value":1775.438504129888,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-astra","source":"arena","metric":"arena_webdev_html_elo_votes","value":1205,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-astra","source":"arena","metric":"arena_webdev_html_elo_interval","value":22.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_webdev_html_elo","value":1753.4333746857742,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_webdev_html_elo_votes","value":135,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_webdev_html_elo_interval","value":60.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_webdev_html_elo","value":1741.0406888051887,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_webdev_html_elo_votes","value":483,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_webdev_html_elo_interval","value":34.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_webdev_html_elo","value":1693.8615951011495,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_webdev_html_elo_votes","value":300,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-wonder","source":"arena","metric":"arena_webdev_html_elo_interval","value":36.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"arena","metric":"arena_webdev_html_elo","value":1686.9166747474715,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"arena","metric":"arena_webdev_html_elo_votes","value":295,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"arena","metric":"arena_webdev_html_elo_interval","value":38.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-sol","source":"arena","metric":"arena_webdev_html_elo","value":1685.2737047533828,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-sol","source":"arena","metric":"arena_webdev_html_elo_votes","value":852,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-sol","source":"arena","metric":"arena_webdev_html_elo_interval","value":23.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_webdev_html_elo","value":1684.1634344201784,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_webdev_html_elo_votes","value":912,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_webdev_html_elo_interval","value":22.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_webdev_html_elo","value":1679.8306317457877,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_webdev_html_elo_votes","value":2295,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_webdev_html_elo_interval","value":14.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_webdev_html_elo","value":1652.7338982209633,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_webdev_html_elo_votes","value":1275,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_webdev_html_elo_interval","value":18.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_webdev_html_elo","value":1650.6878898799823,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_webdev_html_elo_votes","value":2175,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_webdev_html_elo_interval","value":14.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_webdev_html_elo","value":1649.4097560599162,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_webdev_html_elo_votes","value":2529,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_webdev_html_elo_interval","value":13.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_webdev_html_elo","value":1644.0664477694438,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_webdev_html_elo_votes","value":2678,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_webdev_html_elo_interval","value":13.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_webdev_html_elo","value":1642.7238903101838,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_webdev_html_elo_votes","value":185,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-4-argon","source":"arena","metric":"arena_webdev_html_elo_interval","value":48.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_webdev_html_elo","value":1641.0649098880638,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_webdev_html_elo_votes","value":812,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_webdev_html_elo_interval","value":22.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_webdev_html_elo","value":1627.3655959652265,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_webdev_html_elo_votes","value":855,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_webdev_html_elo_interval","value":22.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"tencent/hy4-preview","source":"arena","metric":"arena_webdev_html_elo","value":1620.0511885737506,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"tencent/hy4-preview","source":"arena","metric":"arena_webdev_html_elo_votes","value":708,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"tencent/hy4-preview","source":"arena","metric":"arena_webdev_html_elo_interval","value":24.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_webdev_html_elo","value":1617.5155797607176,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_webdev_html_elo_votes","value":2443,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_webdev_html_elo_interval","value":13.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_webdev_html_elo","value":1616.0878686036008,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_webdev_html_elo_votes","value":1545,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_webdev_html_elo_interval","value":16.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_webdev_html_elo","value":1615.919094177542,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_webdev_html_elo_votes","value":722,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_webdev_html_elo_interval","value":23.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"arena","metric":"arena_webdev_html_elo","value":1611.696400717983,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"arena","metric":"arena_webdev_html_elo_votes","value":608,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"arena","metric":"arena_webdev_html_elo_interval","value":26.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_webdev_html_elo","value":1597.3109218630905,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_webdev_html_elo_votes","value":1670,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_webdev_html_elo_interval","value":15.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-luna","source":"arena","metric":"arena_webdev_html_elo","value":1595.2624045670464,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-luna","source":"arena","metric":"arena_webdev_html_elo_votes","value":3220,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-luna","source":"arena","metric":"arena_webdev_html_elo_interval","value":12.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.3","source":"arena","metric":"arena_webdev_html_elo","value":1595.122380509858,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.3","source":"arena","metric":"arena_webdev_html_elo_votes","value":1304,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.3","source":"arena","metric":"arena_webdev_html_elo_interval","value":17.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_webdev_html_elo","value":1593.4245613633789,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_webdev_html_elo_votes","value":1850,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_webdev_html_elo_interval","value":15.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_webdev_html_elo","value":1577.0803182981315,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_webdev_html_elo_votes","value":2703,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_webdev_html_elo_interval","value":13.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_webdev_html_elo","value":1570.0014968877604,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_webdev_html_elo_votes","value":2462,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_webdev_html_elo_interval","value":13.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-haiku-5.5","source":"arena","metric":"arena_webdev_html_elo","value":1568.8460806000896,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-haiku-5.5","source":"arena","metric":"arena_webdev_html_elo_votes","value":449,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-haiku-5.5","source":"arena","metric":"arena_webdev_html_elo_interval","value":29.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_webdev_html_elo","value":1567.3862080412512,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_webdev_html_elo_votes","value":1599,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_webdev_html_elo_interval","value":16.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"arena","metric":"arena_webdev_html_elo","value":1565.6369185101405,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"arena","metric":"arena_webdev_html_elo_votes","value":548,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4-pro-0813","source":"arena","metric":"arena_webdev_html_elo_interval","value":26.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.2","source":"arena","metric":"arena_webdev_html_elo","value":1565.4786078366437,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.2","source":"arena","metric":"arena_webdev_html_elo_votes","value":2032,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.2","source":"arena","metric":"arena_webdev_html_elo_interval","value":14.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_webdev_html_elo","value":1559.1983322945903,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_webdev_html_elo_votes","value":2462,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_webdev_html_elo_interval","value":13.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_webdev_html_elo","value":1557.8301963958074,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_webdev_html_elo_votes","value":606,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4-flash","source":"arena","metric":"arena_webdev_html_elo_interval","value":25.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_webdev_html_elo","value":1555.903243091917,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_webdev_html_elo_votes","value":722,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_webdev_html_elo_interval","value":23.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_webdev_html_elo","value":1553.6351943653606,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_webdev_html_elo_votes","value":2267,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_webdev_html_elo_interval","value":13.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_webdev_html_elo","value":1547.1709240458995,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_webdev_html_elo_votes","value":922,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_webdev_html_elo_interval","value":20.89,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_webdev_html_elo","value":1542.9242770779356,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_webdev_html_elo_votes","value":1870,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_webdev_html_elo_interval","value":15.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_webdev_html_elo","value":1542.7254677774858,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_webdev_html_elo_votes","value":244,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_webdev_html_elo_interval","value":41.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_webdev_html_elo","value":1542.6595608739397,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_webdev_html_elo_votes","value":2270,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_webdev_html_elo_interval","value":13.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_webdev_html_elo","value":1539.7051763864617,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_webdev_html_elo_votes","value":906,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_webdev_html_elo_interval","value":21.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_webdev_html_elo","value":1526.8111385282825,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_webdev_html_elo_votes","value":2085,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_webdev_html_elo_interval","value":14.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_webdev_html_elo","value":1526.5992284060007,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_webdev_html_elo_votes","value":2897,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_webdev_html_elo_interval","value":11.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_webdev_html_elo","value":1526.2669418127298,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_webdev_html_elo_votes","value":1947,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_webdev_html_elo_interval","value":14.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_webdev_html_elo","value":1522.2546194634774,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_webdev_html_elo_votes","value":1342,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_webdev_html_elo_interval","value":17.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_webdev_html_elo","value":1520.059073227218,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_webdev_html_elo_votes","value":1799,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_webdev_html_elo_interval","value":15.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.7-max","source":"arena","metric":"arena_webdev_html_elo","value":1511.5045944659537,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.7-max","source":"arena","metric":"arena_webdev_html_elo_votes","value":1044,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.7-max","source":"arena","metric":"arena_webdev_html_elo_interval","value":19.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_webdev_html_elo","value":1510.1390846806582,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_webdev_html_elo_votes","value":6278,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_webdev_html_elo_interval","value":12.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_webdev_html_elo","value":1507.8244539051532,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_webdev_html_elo_votes","value":1208,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.1","source":"arena","metric":"arena_webdev_html_elo_interval","value":18.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-open","source":"arena","metric":"arena_webdev_html_elo","value":1495.2585737565366,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-open","source":"arena","metric":"arena_webdev_html_elo_votes","value":173,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-open","source":"arena","metric":"arena_webdev_html_elo_interval","value":48.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_webdev_html_elo","value":1489.6100984114723,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_webdev_html_elo_votes","value":2621,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_webdev_html_elo_interval","value":12.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_webdev_html_elo","value":1487.0462031315117,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_webdev_html_elo_votes","value":374,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_webdev_html_elo_interval","value":35.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_webdev_html_elo","value":1486.651034528798,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_webdev_html_elo_votes","value":970,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"tencent/hy3","source":"arena","metric":"arena_webdev_html_elo_interval","value":20.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_webdev_html_elo","value":1484.5365944705923,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_webdev_html_elo_votes","value":1161,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_webdev_html_elo_interval","value":18.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_webdev_html_elo","value":1477.8032181462459,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_webdev_html_elo_votes","value":132,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_webdev_html_elo_interval","value":52.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_webdev_html_elo","value":1472.5778908344867,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_webdev_html_elo_votes","value":2896,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"arena","metric":"arena_webdev_html_elo_interval","value":11.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_webdev_html_elo","value":1462.65188149481,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_webdev_html_elo_votes","value":2085,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_webdev_html_elo_interval","value":13.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_webdev_html_elo","value":1454.6959702527201,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_webdev_html_elo_votes","value":2689,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_webdev_html_elo_interval","value":12.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.7-code","source":"arena","metric":"arena_webdev_html_elo","value":1450.6429486995835,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.7-code","source":"arena","metric":"arena_webdev_html_elo_votes","value":669,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.7-code","source":"arena","metric":"arena_webdev_html_elo_interval","value":24.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_webdev_html_elo","value":1450.243811819489,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_webdev_html_elo_votes","value":890,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5","source":"arena","metric":"arena_webdev_html_elo_interval","value":20.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_webdev_html_elo","value":1446.6148735635386,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_webdev_html_elo_votes","value":3892,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-4.7","source":"arena","metric":"arena_webdev_html_elo_interval","value":13.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"reflection/beam-1.0-501b-a23b","source":"arena","metric":"arena_webdev_html_elo","value":1436.1848491975875,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"reflection/beam-1.0-501b-a23b","source":"arena","metric":"arena_webdev_html_elo_votes","value":405,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"reflection/beam-1.0-501b-a23b","source":"arena","metric":"arena_webdev_html_elo_interval","value":34.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_webdev_html_elo","value":1434.7414933435548,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_webdev_html_elo_votes","value":1502,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4-pro","source":"arena","metric":"arena_webdev_html_elo_interval","value":15.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_webdev_html_elo","value":1429.4250998874138,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_webdev_html_elo_votes","value":1757,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_webdev_html_elo_interval","value":14.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_webdev_html_elo","value":1426.7680058373307,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_webdev_html_elo_votes","value":1081,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_webdev_html_elo_interval","value":23.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_webdev_html_elo","value":1426.654408458594,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_webdev_html_elo_votes","value":3092,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_webdev_html_elo_interval","value":16.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_webdev_html_elo","value":1426.3258314686982,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_webdev_html_elo_votes","value":2585,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_webdev_html_elo_interval","value":12.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.3-codex","source":"arena","metric":"arena_webdev_html_elo","value":1421.661130146073,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.3-codex","source":"arena","metric":"arena_webdev_html_elo_votes","value":399,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.3-codex","source":"arena","metric":"arena_webdev_html_elo_interval","value":31.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_webdev_html_elo","value":1419.071888154665,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_webdev_html_elo_votes","value":1438,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_webdev_html_elo_interval","value":16.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_webdev_html_elo","value":1413.5666817139947,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_webdev_html_elo_votes","value":965,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m2.5","source":"arena","metric":"arena_webdev_html_elo_interval","value":20.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_webdev_html_elo","value":1409.625361532455,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_webdev_html_elo_votes","value":2604,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_webdev_html_elo_interval","value":12.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_webdev_html_elo","value":1405.2580540724139,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_webdev_html_elo_votes","value":4890,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_webdev_html_elo_interval","value":13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_webdev_html_elo","value":1401.3738893474,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_webdev_html_elo_votes","value":1976,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m2.7","source":"arena","metric":"arena_webdev_html_elo_interval","value":14.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_webdev_html_elo","value":1399.3904738400722,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_webdev_html_elo_votes","value":2174,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"thinkingmachines/inkling","source":"arena","metric":"arena_webdev_html_elo_interval","value":14.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_webdev_html_elo","value":1398.9037250532324,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_webdev_html_elo_votes","value":9077,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_webdev_html_elo_interval","value":11.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_webdev_html_elo","value":1398.7425494184386,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_webdev_html_elo_votes","value":6911,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.1","source":"arena","metric":"arena_webdev_html_elo_interval","value":12.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_webdev_html_elo","value":1397.7432895413592,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_webdev_html_elo_votes","value":632,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_webdev_html_elo_interval","value":25.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_webdev_html_elo","value":1385.660457308411,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_webdev_html_elo_votes","value":934,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_webdev_html_elo_interval","value":20.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_webdev_html_elo","value":1379.532533905005,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_webdev_html_elo_votes","value":2025,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_webdev_html_elo_interval","value":14.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_webdev_html_elo","value":1370.6316455419221,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_webdev_html_elo_votes","value":813,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"upstage/solar-pro4","source":"arena","metric":"arena_webdev_html_elo_interval","value":23.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_webdev_html_elo","value":1370.591057839043,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_webdev_html_elo_votes","value":3269,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v3.2","source":"arena","metric":"arena_webdev_html_elo_interval","value":13.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_webdev_html_elo","value":1366.8095905387609,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_webdev_html_elo_votes","value":1769,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_webdev_html_elo_interval","value":15.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_webdev_html_elo","value":1361.9107379637708,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_webdev_html_elo_votes","value":205,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_webdev_html_elo_interval","value":43.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_webdev_html_elo","value":1356.1367572421832,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_webdev_html_elo_votes","value":247,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_webdev_html_elo_interval","value":42.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"tencent/hy3-preview","source":"arena","metric":"arena_webdev_html_elo","value":1355.8060972048659,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"tencent/hy3-preview","source":"arena","metric":"arena_webdev_html_elo_votes","value":201,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"tencent/hy3-preview","source":"arena","metric":"arena_webdev_html_elo_interval","value":44.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_webdev_html_elo","value":1351.4964362012292,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_webdev_html_elo_votes","value":988,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_webdev_html_elo_interval","value":20.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_webdev_html_elo","value":1350.2595364448648,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_webdev_html_elo_votes","value":6755,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-4.6","source":"arena","metric":"arena_webdev_html_elo_interval","value":12.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.2-codex","source":"arena","metric":"arena_webdev_html_elo","value":1348.3905375739141,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.2-codex","source":"arena","metric":"arena_webdev_html_elo_votes","value":2359,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.2-codex","source":"arena","metric":"arena_webdev_html_elo_interval","value":15.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.1-codex","source":"arena","metric":"arena_webdev_html_elo","value":1346.1319539528185,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.1-codex","source":"arena","metric":"arena_webdev_html_elo_votes","value":4991,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.1-codex","source":"arena","metric":"arena_webdev_html_elo_interval","value":13.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_webdev_html_elo","value":1317.9154157107241,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_webdev_html_elo_votes","value":10648,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_webdev_html_elo_interval","value":9.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_webdev_html_elo","value":1307.6045656662561,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_webdev_html_elo_votes","value":261,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_webdev_html_elo_interval","value":41.27,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_webdev_html_elo","value":1306.3497906524638,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_webdev_html_elo_votes","value":6685,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m2","source":"arena","metric":"arena_webdev_html_elo_interval","value":12.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_webdev_html_elo","value":1301.2510669846301,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_webdev_html_elo_votes","value":193,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-35b-a3b","source":"arena","metric":"arena_webdev_html_elo_interval","value":44.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_webdev_html_elo","value":1290.7424690932942,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_webdev_html_elo_votes","value":124,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.5-flash-02-23","source":"arena","metric":"arena_webdev_html_elo_interval","value":59.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_webdev_html_elo","value":1286.943673760078,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_webdev_html_elo_votes","value":8578,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3-coder","source":"arena","metric":"arena_webdev_html_elo_interval","value":11.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_webdev_html_elo","value":1281.062464397714,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_webdev_html_elo_votes","value":3969,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"arena","metric":"arena_webdev_html_elo_interval","value":14.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_webdev_html_elo","value":1276.3126571903877,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_webdev_html_elo_votes","value":1753,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_webdev_html_elo_interval","value":16.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.1-codex-mini","source":"arena","metric":"arena_webdev_html_elo","value":1252.8191621020655,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.1-codex-mini","source":"arena","metric":"arena_webdev_html_elo_votes","value":1154,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.1-codex-mini","source":"arena","metric":"arena_webdev_html_elo_interval","value":22.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_webdev_html_elo","value":1240.014159024718,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_webdev_html_elo_votes","value":192,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"arcee-ai/trinity-large-thinking","source":"arena","metric":"arena_webdev_html_elo_interval","value":49.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_webdev_html_elo","value":1234.826832749961,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_webdev_html_elo_votes","value":2730,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_webdev_html_elo_interval","value":16.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_webdev_html_elo","value":1199.151344432888,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_webdev_html_elo_votes","value":108,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"inception/mercury-2","source":"arena","metric":"arena_webdev_html_elo_interval","value":66.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_webdev_from_image_elo","value":1752.570372559565,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":781,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":24.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_webdev_from_image_elo","value":1737.13977654562,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":1551,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":16.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-astra","source":"arena","metric":"arena_webdev_from_image_elo","value":1726.2123270395787,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-astra","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":3181,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-astra","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":12.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_webdev_from_image_elo","value":1722.2191243605344,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":2907,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":12.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6.1-sol","source":"arena","metric":"arena_webdev_from_image_elo","value":1701.7353202057543,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6.1-sol","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":1916,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6.1-sol","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":15.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_webdev_from_image_elo","value":1661.818933892443,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":4671,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":9.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-sol","source":"arena","metric":"arena_webdev_from_image_elo","value":1660.4795899286519,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-sol","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":2948,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-sol","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":11.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_webdev_from_image_elo","value":1640.3894130603526,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":5679,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":9.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_webdev_from_image_elo","value":1636.588360038123,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":1163,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":18.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_webdev_from_image_elo","value":1622.832844095668,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":5855,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":8.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_webdev_from_image_elo","value":1609.1660278108561,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":4969,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":9.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"arena","metric":"arena_webdev_from_image_elo","value":1606.3300077467948,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":767,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":22.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_webdev_from_image_elo","value":1603.4685699827546,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":3241,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":11.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_webdev_from_image_elo","value":1599.4880112260375,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":2661,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":12.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_webdev_from_image_elo","value":1598.2805724829486,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":2627,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":12.27,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_webdev_from_image_elo","value":1595.540797821539,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":2318,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":12.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_webdev_from_image_elo","value":1592.7182186745918,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":2516,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":12.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_webdev_from_image_elo","value":1585.5228937193829,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":1191,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":17.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_webdev_from_image_elo","value":1578.7771939256486,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":3936,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k3","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":10.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_webdev_from_image_elo","value":1578.3233115154308,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":5623,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":9.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_webdev_from_image_elo","value":1577.4720619505188,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":6946,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":9.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_webdev_from_image_elo","value":1577.4376341509046,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":6418,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":8.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-luna","source":"arena","metric":"arena_webdev_from_image_elo","value":1571.1091362324723,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-luna","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":4439,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-6-luna","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":9.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_webdev_from_image_elo","value":1561.680956859373,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":4255,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":9.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_webdev_from_image_elo","value":1550.4117076786192,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":3300,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":11.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_webdev_from_image_elo","value":1545.4402389582183,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":1797,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":14.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_webdev_from_image_elo","value":1542.7388042338378,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":7938,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":8.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_webdev_from_image_elo","value":1540.5135030783572,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":4814,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":9.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_webdev_from_image_elo","value":1539.8619506829148,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":8124,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":7.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_webdev_from_image_elo","value":1539.5800033313958,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":3120,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":11.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_webdev_from_image_elo","value":1532.0859592631377,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":6795,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":9.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_webdev_from_image_elo","value":1529.4437015743492,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":8312,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":8.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_webdev_from_image_elo","value":1520.8565093692084,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":3591,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":11.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_webdev_from_image_elo","value":1516.9857288035832,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":4324,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":9.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.7-code","source":"arena","metric":"arena_webdev_from_image_elo","value":1512.8898692988346,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.7-code","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":921,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.7-code","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":20.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_webdev_from_image_elo","value":1504.3704894073348,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":2865,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":11.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_webdev_from_image_elo","value":1481.080824712114,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":8219,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":8.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_webdev_from_image_elo","value":1472.085258620029,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":5847,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"qwen/qwen3.6-plus","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":10.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_webdev_from_image_elo","value":1470.3442173295377,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":5983,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":8.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_webdev_from_image_elo","value":1447.7003955547596,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":1603,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":15.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.3-codex","source":"arena","metric":"arena_webdev_from_image_elo","value":1443.1392834315347,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.3-codex","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":2671,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.3-codex","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":14.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_webdev_from_image_elo","value":1439.387657578004,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":1653,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":17.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_webdev_from_image_elo","value":1436.4605011545846,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":3201,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":11.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_webdev_from_image_elo","value":1424.9367678303793,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":1560,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":16.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_webdev_from_image_elo","value":1420.5883661869084,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":1000,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":21.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_webdev_from_image_elo","value":1410.0181024237877,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":1025,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":19.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_webdev_from_image_elo","value":1374.788586854159,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":5868,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":9.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_webdev_from_image_elo","value":1336.4001935413132,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":6518,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":10.89,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_webdev_from_image_elo","value":1285.4095058025518,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_webdev_from_image_elo_votes","value":1053,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_webdev_from_image_elo_interval","value":21.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/webdev"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_vision_english_elo","value":1323.8274563693385,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_vision_english_elo_votes","value":9235,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_vision_english_elo_interval","value":8.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_vision_english_elo","value":1323.1501874517471,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_vision_english_elo_votes","value":5874,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_vision_english_elo_interval","value":9.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_vision_english_elo","value":1321.9357100703787,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_vision_english_elo_votes","value":9834,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_vision_english_elo_interval","value":8.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_vision_english_elo","value":1317.7779705764565,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_vision_english_elo_votes","value":1556,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_vision_english_elo_interval","value":15.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_vision_english_elo","value":1316.9371761587845,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_vision_english_elo_votes","value":992,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_vision_english_elo_interval","value":19.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_vision_english_elo","value":1314.5092640522453,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_vision_english_elo_votes","value":6237,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_vision_english_elo_interval","value":9.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_vision_english_elo","value":1312.7378944489988,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_vision_english_elo_votes","value":1825,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_vision_english_elo_interval","value":14.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_vision_english_elo","value":1310.5570632717968,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_vision_english_elo_votes","value":3284,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_vision_english_elo_interval","value":11.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_vision_english_elo","value":1308.9962617939618,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_vision_english_elo_votes","value":1848,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_vision_english_elo_interval","value":14.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_vision_english_elo","value":1305.3311509433038,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_vision_english_elo_votes","value":5040,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_vision_english_elo_interval","value":9.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_vision_english_elo","value":1300.6170846851023,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_vision_english_elo_votes","value":12132,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_vision_english_elo_interval","value":7.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_vision_english_elo","value":1298.1971496447068,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_vision_english_elo_votes","value":11555,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_vision_english_elo_interval","value":8.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_vision_english_elo","value":1298.0862215170168,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_vision_english_elo_votes","value":1877,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_vision_english_elo_interval","value":14.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_vision_english_elo","value":1295.4233667088674,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_vision_english_elo_votes","value":5043,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_vision_english_elo_interval","value":9.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_vision_english_elo","value":1294.7944069626483,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_vision_english_elo_votes","value":3098,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_vision_english_elo_interval","value":11.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_vision_english_elo","value":1293.0695506537136,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_vision_english_elo_votes","value":7311,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_vision_english_elo_interval","value":9.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_vision_english_elo","value":1292.262193164126,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_vision_english_elo_votes","value":11422,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_vision_english_elo_interval","value":8.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_vision_english_elo","value":1291.9845352160314,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_vision_english_elo_votes","value":4266,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_vision_english_elo_interval","value":10.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_vision_english_elo","value":1291.3610998810464,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_vision_english_elo_votes","value":695,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_vision_english_elo_interval","value":23.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_vision_english_elo","value":1290.3753869427578,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_vision_english_elo_votes","value":513,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_vision_english_elo_interval","value":26.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_vision_english_elo","value":1289.101222580443,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_vision_english_elo_votes","value":859,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_vision_english_elo_interval","value":20.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"arena","metric":"arena_vision_english_elo","value":1288.1152414667713,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"arena","metric":"arena_vision_english_elo_votes","value":1301,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"arena","metric":"arena_vision_english_elo_interval","value":17.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_vision_english_elo","value":1287.118278177235,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_vision_english_elo_votes","value":18497,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_vision_english_elo_interval","value":7.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_vision_english_elo","value":1286.8635906338923,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_vision_english_elo_votes","value":6756,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_vision_english_elo_interval","value":9.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_vision_english_elo","value":1284.6484156040874,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_vision_english_elo_votes","value":4285,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_vision_english_elo_interval","value":10.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_vision_english_elo","value":1283.2047496718046,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_vision_english_elo_votes","value":355,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_vision_english_elo_interval","value":31.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_vision_english_elo","value":1280.3569722428838,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_vision_english_elo_votes","value":5067,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_vision_english_elo_interval","value":9.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_vision_english_elo","value":1280.2633181467268,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_vision_english_elo_votes","value":3912,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_vision_english_elo_interval","value":10.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-astra","source":"arena","metric":"arena_vision_english_elo","value":1280.2508195108771,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-astra","source":"arena","metric":"arena_vision_english_elo_votes","value":1343,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-astra","source":"arena","metric":"arena_vision_english_elo_interval","value":16.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_vision_english_elo","value":1274.7244595567777,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_vision_english_elo_votes","value":5335,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_vision_english_elo_interval","value":9.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_vision_english_elo","value":1274.3471630545278,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_vision_english_elo_votes","value":17081,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_vision_english_elo_interval","value":7.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_vision_english_elo","value":1273.9752640183742,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_vision_english_elo_votes","value":10972,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_vision_english_elo_interval","value":7.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6.1-sol","source":"arena","metric":"arena_vision_english_elo","value":1273.68685263208,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6.1-sol","source":"arena","metric":"arena_vision_english_elo_votes","value":774,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6.1-sol","source":"arena","metric":"arena_vision_english_elo_interval","value":21.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_vision_english_elo","value":1271.8738268258485,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_vision_english_elo_votes","value":4052,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_vision_english_elo_interval","value":10.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_vision_english_elo","value":1270.962645956663,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_vision_english_elo_votes","value":15807,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_vision_english_elo_interval","value":7.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_vision_english_elo","value":1269.541471697808,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_vision_english_elo_votes","value":2512,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_vision_english_elo_interval","value":12.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_vision_english_elo","value":1269.445945866777,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_vision_english_elo_votes","value":1134,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_vision_english_elo_interval","value":18.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_vision_english_elo","value":1268.953435316997,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_vision_english_elo_votes","value":3159,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_vision_english_elo_interval","value":11.67,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_vision_english_elo","value":1268.4533140856306,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_vision_english_elo_votes","value":12659,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_vision_english_elo_interval","value":7.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_vision_english_elo","value":1267.7810444536299,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_vision_english_elo_votes","value":612,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_vision_english_elo_interval","value":24.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_vision_english_elo","value":1266.7398360465568,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_vision_english_elo_votes","value":2445,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_vision_english_elo_interval","value":12.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_vision_english_elo","value":1262.5593207518555,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_vision_english_elo_votes","value":7372,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_vision_english_elo_interval","value":8.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_vision_english_elo","value":1262.5279553548758,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_vision_english_elo_votes","value":3794,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_vision_english_elo_interval","value":10.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_vision_english_elo","value":1260.9808948112159,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_vision_english_elo_votes","value":40672,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_vision_english_elo_interval","value":6.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_vision_english_elo","value":1258.727116435697,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_vision_english_elo_votes","value":11479,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_vision_english_elo_interval","value":8.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_vision_english_elo","value":1256.0412424509427,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_vision_english_elo_votes","value":9635,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_vision_english_elo_interval","value":8.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_vision_english_elo","value":1255.7723519477486,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_vision_english_elo_votes","value":4605,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_vision_english_elo_interval","value":9.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_vision_english_elo","value":1251.6630162084052,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_vision_english_elo_votes","value":3532,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_vision_english_elo_interval","value":11.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_vision_english_elo","value":1248.5922196481083,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_vision_english_elo_votes","value":5296,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_vision_english_elo_interval","value":9.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_vision_english_elo","value":1245.9979248519403,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_vision_english_elo_votes","value":11800,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_vision_english_elo_interval","value":7.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_vision_english_elo","value":1244.0788504103616,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_vision_english_elo_votes","value":10694,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_vision_english_elo_interval","value":8.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_vision_english_elo","value":1243.187462671484,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_vision_english_elo_votes","value":7347,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_vision_english_elo_interval","value":8.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_vision_english_elo","value":1242.6143395320018,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_vision_english_elo_votes","value":2816,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_vision_english_elo_interval","value":12.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_vision_english_elo","value":1240.440494478209,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_vision_english_elo_votes","value":2314,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_vision_english_elo_interval","value":13.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_vision_english_elo","value":1239.366207014783,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_vision_english_elo_votes","value":25447,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_vision_english_elo_interval","value":6.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_vision_english_elo","value":1235.1746411258355,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_vision_english_elo_votes","value":11160,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_vision_english_elo_interval","value":8.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_vision_english_elo","value":1232.06564753358,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_vision_english_elo_votes","value":11005,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_vision_english_elo_interval","value":8.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_vision_english_elo","value":1231.3598674769255,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_vision_english_elo_votes","value":18691,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_vision_english_elo_interval","value":9.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-sol","source":"arena","metric":"arena_vision_english_elo","value":1228.6488791722313,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-sol","source":"arena","metric":"arena_vision_english_elo_votes","value":1058,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-sol","source":"arena","metric":"arena_vision_english_elo_interval","value":19.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_vision_english_elo","value":1228.5022930564319,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_vision_english_elo_votes","value":1292,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_vision_english_elo_interval","value":17.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o3","source":"arena","metric":"arena_vision_english_elo","value":1221.3915581375277,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o3","source":"arena","metric":"arena_vision_english_elo_votes","value":21609,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o3","source":"arena","metric":"arena_vision_english_elo_interval","value":8.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_vision_english_elo","value":1215.939043817838,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_vision_english_elo_votes","value":13428,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_vision_english_elo_interval","value":10.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_vision_english_elo","value":1209.3708707666315,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_vision_english_elo_votes","value":19011,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_vision_english_elo_interval","value":9.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-luna","source":"arena","metric":"arena_vision_english_elo","value":1204.4764915388328,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-luna","source":"arena","metric":"arena_vision_english_elo_votes","value":1264,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-luna","source":"arena","metric":"arena_vision_english_elo_interval","value":18.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_vision_english_elo","value":1201.671894422333,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_vision_english_elo_votes","value":10341,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_vision_english_elo_interval","value":8.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_vision_english_elo","value":1199.7668948951564,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_vision_english_elo_votes","value":19813,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_vision_english_elo_interval","value":9.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_vision_english_elo","value":1190.5563032050673,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_vision_english_elo_votes","value":19159,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_vision_english_elo_interval","value":9.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_vision_english_elo","value":1188.222184536285,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_vision_english_elo_votes","value":7938,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_vision_english_elo_interval","value":10.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_vision_english_elo","value":1183.0363028732318,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_vision_english_elo_votes","value":1596,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_vision_english_elo_interval","value":15.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3.1","source":"arena","metric":"arena_vision_english_elo","value":1179.047597528347,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3.1","source":"arena","metric":"arena_vision_english_elo_votes","value":19018,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3.1","source":"arena","metric":"arena_vision_english_elo_interval","value":8.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_vision_english_elo","value":1178.777414392367,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_vision_english_elo_votes","value":914,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_vision_english_elo_interval","value":19.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3","source":"arena","metric":"arena_vision_english_elo","value":1172.032765997719,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3","source":"arena","metric":"arena_vision_english_elo_votes","value":5311,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3","source":"arena","metric":"arena_vision_english_elo_interval","value":10.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_vision_english_elo","value":1170.0233902022958,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_vision_english_elo_votes","value":1783,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_vision_english_elo_interval","value":15.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o1","source":"arena","metric":"arena_vision_english_elo","value":1162.3141177944767,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o1","source":"arena","metric":"arena_vision_english_elo_votes","value":1943,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o1","source":"arena","metric":"arena_vision_english_elo_interval","value":14.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_vision_english_elo","value":1157.1847199262465,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_vision_english_elo_votes","value":14751,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_vision_english_elo_interval","value":10.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_vision_english_elo","value":1149.9864262416813,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_vision_english_elo_votes","value":3387,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_vision_english_elo_interval","value":11.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_vision_english_elo","value":1147.0450215869814,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_vision_english_elo_votes","value":14077,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_vision_english_elo_interval","value":11.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_vision_english_elo","value":1143.2853213617263,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_vision_english_elo_votes","value":3098,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_vision_english_elo_interval","value":12.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen2.5-vl-72b-instruct","source":"arena","metric":"arena_vision_english_elo","value":1114.8440792754195,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen2.5-vl-72b-instruct","source":"arena","metric":"arena_vision_english_elo_votes","value":2169,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen2.5-vl-72b-instruct","source":"arena","metric":"arena_vision_english_elo_interval","value":13.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_vision_english_elo","value":1100.7934626837023,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_vision_english_elo_votes","value":461,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-nano","source":"arena","metric":"arena_vision_english_elo_interval","value":26.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4-turbo","source":"arena","metric":"arena_vision_english_elo","value":1096.576778851849,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4-turbo","source":"arena","metric":"arena_vision_english_elo_votes","value":8417,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4-turbo","source":"arena","metric":"arena_vision_english_elo_interval","value":13.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_vision_english_elo","value":1072.4423146623612,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_vision_english_elo_votes","value":10721,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_vision_english_elo_interval","value":10.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_vision_english_elo","value":1071.9144609462342,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_vision_english_elo_votes","value":1744,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_vision_english_elo_interval","value":16.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"amazon/nova-lite-v1","source":"arena","metric":"arena_vision_english_elo","value":998.8917005230089,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"amazon/nova-lite-v1","source":"arena","metric":"arena_vision_english_elo_votes","value":1048,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"amazon/nova-lite-v1","source":"arena","metric":"arena_vision_english_elo_interval","value":19.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"amazon/nova-pro-v1","source":"arena","metric":"arena_vision_english_elo","value":986.7633888305295,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"amazon/nova-pro-v1","source":"arena","metric":"arena_vision_english_elo_votes","value":1264,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"amazon/nova-pro-v1","source":"arena","metric":"arena_vision_english_elo_interval","value":18.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_vision_chinese_elo","value":1416.0843379029016,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_vision_chinese_elo_votes","value":224,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_vision_chinese_elo_interval","value":39.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_vision_chinese_elo","value":1400.387166976013,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_vision_chinese_elo_votes","value":1037,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_vision_chinese_elo_interval","value":20.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_vision_chinese_elo","value":1394.1059568384335,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_vision_chinese_elo_votes","value":302,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_vision_chinese_elo_interval","value":34.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_vision_chinese_elo","value":1391.1367829374449,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_vision_chinese_elo_votes","value":284,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_vision_chinese_elo_interval","value":34.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_vision_chinese_elo","value":1384.4279856726387,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_vision_chinese_elo_votes","value":257,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_vision_chinese_elo_interval","value":36.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_vision_chinese_elo","value":1377.065533142831,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_vision_chinese_elo_votes","value":847,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_vision_chinese_elo_interval","value":22.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_vision_chinese_elo","value":1372.7727144688824,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_vision_chinese_elo_votes","value":784,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_vision_chinese_elo_interval","value":22.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_vision_chinese_elo","value":1371.041080621802,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_vision_chinese_elo_votes","value":1504,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_vision_chinese_elo_interval","value":17.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_vision_chinese_elo","value":1370.3195668722983,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_vision_chinese_elo_votes","value":1681,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_vision_chinese_elo_interval","value":17.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_vision_chinese_elo","value":1363.8153952917796,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_vision_chinese_elo_votes","value":3186,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_vision_chinese_elo_interval","value":13.27,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_vision_chinese_elo","value":1362.7898492567551,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_vision_chinese_elo_votes","value":699,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_vision_chinese_elo_interval","value":23.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-astra","source":"arena","metric":"arena_vision_chinese_elo","value":1361.1607425257414,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-astra","source":"arena","metric":"arena_vision_chinese_elo_votes","value":259,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-astra","source":"arena","metric":"arena_vision_chinese_elo_interval","value":37.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_vision_chinese_elo","value":1360.0916508118032,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_vision_chinese_elo_votes","value":1777,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_vision_chinese_elo_interval","value":16.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_vision_chinese_elo","value":1357.8958612377721,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_vision_chinese_elo_votes","value":541,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_vision_chinese_elo_interval","value":26.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_vision_chinese_elo","value":1356.9261228252938,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_vision_chinese_elo_votes","value":536,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_vision_chinese_elo_interval","value":26.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_vision_chinese_elo","value":1353.962092611682,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_vision_chinese_elo_votes","value":1846,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_vision_chinese_elo_interval","value":16.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_vision_chinese_elo","value":1348.3429086766755,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_vision_chinese_elo_votes","value":767,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_vision_chinese_elo_interval","value":22.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_vision_chinese_elo","value":1345.9789728889502,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_vision_chinese_elo_votes","value":1027,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_vision_chinese_elo_interval","value":20.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_vision_chinese_elo","value":1345.560862120775,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_vision_chinese_elo_votes","value":1131,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_vision_chinese_elo_interval","value":19.6,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_vision_chinese_elo","value":1344.778390621269,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_vision_chinese_elo_votes","value":728,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_vision_chinese_elo_interval","value":23.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_vision_chinese_elo","value":1336.7190736213865,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_vision_chinese_elo_votes","value":682,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_vision_chinese_elo_interval","value":23.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_vision_chinese_elo","value":1331.635669020893,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_vision_chinese_elo_votes","value":740,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_vision_chinese_elo_interval","value":22.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_vision_chinese_elo","value":1330.6510622904786,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_vision_chinese_elo_votes","value":847,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_vision_chinese_elo_interval","value":21.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_vision_chinese_elo","value":1329.1448159576428,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_vision_chinese_elo_votes","value":2644,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_vision_chinese_elo_interval","value":14.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_vision_chinese_elo","value":1328.4682799839145,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_vision_chinese_elo_votes","value":273,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_vision_chinese_elo_interval","value":34.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"arena","metric":"arena_vision_chinese_elo","value":1327.267086403513,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"arena","metric":"arena_vision_chinese_elo_votes","value":199,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"arena","metric":"arena_vision_chinese_elo_interval","value":41.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_vision_chinese_elo","value":1325.8485587778885,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_vision_chinese_elo_votes","value":2734,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_vision_chinese_elo_interval","value":14.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_vision_chinese_elo","value":1325.5678259146455,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_vision_chinese_elo_votes","value":1580,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_vision_chinese_elo_interval","value":17.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_vision_chinese_elo","value":1325.530808132724,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_vision_chinese_elo_votes","value":409,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_vision_chinese_elo_interval","value":29.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_vision_chinese_elo","value":1313.9609595219395,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_vision_chinese_elo_votes","value":2045,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_vision_chinese_elo_interval","value":15.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_vision_chinese_elo","value":1312.552453794647,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_vision_chinese_elo_votes","value":677,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_vision_chinese_elo_interval","value":23.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_vision_chinese_elo","value":1312.4924093711375,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_vision_chinese_elo_votes","value":1609,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_vision_chinese_elo_interval","value":17.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_vision_chinese_elo","value":1311.0829185183948,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_vision_chinese_elo_votes","value":1048,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_vision_chinese_elo_interval","value":20.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_vision_chinese_elo","value":1310.6153073770736,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_vision_chinese_elo_votes","value":524,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_vision_chinese_elo_interval","value":26.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_vision_chinese_elo","value":1307.1115698456329,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_vision_chinese_elo_votes","value":1736,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_vision_chinese_elo_interval","value":16.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_vision_chinese_elo","value":1304.8361998345263,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_vision_chinese_elo_votes","value":1351,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_vision_chinese_elo_interval","value":17.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_vision_chinese_elo","value":1300.7980399592495,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_vision_chinese_elo_votes","value":1011,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_vision_chinese_elo_interval","value":20.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_vision_chinese_elo","value":1300.5112705237486,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_vision_chinese_elo_votes","value":1997,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_vision_chinese_elo_interval","value":15.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_vision_chinese_elo","value":1300.1780954784963,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_vision_chinese_elo_votes","value":4797,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_vision_chinese_elo_interval","value":12.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_vision_chinese_elo","value":1293.6357915051103,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_vision_chinese_elo_votes","value":631,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_vision_chinese_elo_interval","value":24.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_vision_chinese_elo","value":1292.404569301714,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_vision_chinese_elo_votes","value":461,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_vision_chinese_elo_interval","value":28.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_vision_chinese_elo","value":1289.283462881059,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_vision_chinese_elo_votes","value":380,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_vision_chinese_elo_interval","value":30.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_vision_chinese_elo","value":1286.1698246055905,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_vision_chinese_elo_votes","value":1661,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_vision_chinese_elo_interval","value":17.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_vision_chinese_elo","value":1284.4043286903836,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_vision_chinese_elo_votes","value":3692,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_vision_chinese_elo_interval","value":13.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_vision_chinese_elo","value":1283.0436924201372,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_vision_chinese_elo_votes","value":998,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_vision_chinese_elo_interval","value":19.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_vision_chinese_elo","value":1277.7363395714083,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_vision_chinese_elo_votes","value":1989,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_vision_chinese_elo_interval","value":15.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_vision_chinese_elo","value":1270.2931608048948,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_vision_chinese_elo_votes","value":671,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_vision_chinese_elo_interval","value":23.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_vision_chinese_elo","value":1267.3772853913797,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_vision_chinese_elo_votes","value":2052,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_vision_chinese_elo_interval","value":16.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-luna","source":"arena","metric":"arena_vision_chinese_elo","value":1266.1796511927982,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-luna","source":"arena","metric":"arena_vision_chinese_elo_votes","value":169,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-luna","source":"arena","metric":"arena_vision_chinese_elo_interval","value":43.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_vision_chinese_elo","value":1256.548862577977,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_vision_chinese_elo_votes","value":1650,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_vision_chinese_elo_interval","value":17.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_vision_chinese_elo","value":1250.0280633413452,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_vision_chinese_elo_votes","value":182,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_vision_chinese_elo_interval","value":44.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_vision_chinese_elo","value":1243.875712172996,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_vision_chinese_elo_votes","value":287,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_vision_chinese_elo_interval","value":37.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o3","source":"arena","metric":"arena_vision_chinese_elo","value":1237.4552438998855,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o3","source":"arena","metric":"arena_vision_chinese_elo_votes","value":2258,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o3","source":"arena","metric":"arena_vision_chinese_elo_interval","value":16.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o1","source":"arena","metric":"arena_vision_chinese_elo","value":1235.098617392637,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o1","source":"arena","metric":"arena_vision_chinese_elo_votes","value":99,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o1","source":"arena","metric":"arena_vision_chinese_elo_interval","value":58.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_vision_chinese_elo","value":1232.3557625312205,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_vision_chinese_elo_votes","value":1739,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_vision_chinese_elo_interval","value":17.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_vision_chinese_elo","value":1226.42509281476,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_vision_chinese_elo_votes","value":1978,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_vision_chinese_elo_interval","value":16.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_vision_chinese_elo","value":1218.011151133092,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_vision_chinese_elo_votes","value":1934,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_vision_chinese_elo_interval","value":17.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_vision_chinese_elo","value":1216.8225039968129,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_vision_chinese_elo_votes","value":166,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_vision_chinese_elo_interval","value":41.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_vision_chinese_elo","value":1213.7626993667068,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_vision_chinese_elo_votes","value":1600,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_vision_chinese_elo_interval","value":18.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3.1","source":"arena","metric":"arena_vision_chinese_elo","value":1189.9089039717724,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3.1","source":"arena","metric":"arena_vision_chinese_elo_votes","value":2176,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3.1","source":"arena","metric":"arena_vision_chinese_elo_interval","value":16.08,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_vision_chinese_elo","value":1185.6913556840027,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_vision_chinese_elo_votes","value":1778,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_vision_chinese_elo_interval","value":17.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_vision_chinese_elo","value":1175.772181298382,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_vision_chinese_elo_votes","value":189,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_vision_chinese_elo_interval","value":43.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_vision_chinese_elo","value":1163.668923848267,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_vision_chinese_elo_votes","value":1020,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_vision_chinese_elo_interval","value":20.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3","source":"arena","metric":"arena_vision_chinese_elo","value":1160.9874874655209,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3","source":"arena","metric":"arena_vision_chinese_elo_votes","value":599,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3","source":"arena","metric":"arena_vision_chinese_elo_interval","value":25.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_vision_chinese_elo","value":1155.147696425525,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_vision_chinese_elo_votes","value":1251,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_vision_chinese_elo_interval","value":20.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_vision_chinese_elo","value":1140.8315081016071,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_vision_chinese_elo_votes","value":294,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_vision_chinese_elo_interval","value":34.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_vision_chinese_elo","value":1132.2433124178356,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_vision_chinese_elo_votes","value":1472,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4o-2024-05-13","source":"arena","metric":"arena_vision_chinese_elo_interval","value":38.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen2.5-vl-72b-instruct","source":"arena","metric":"arena_vision_chinese_elo","value":1107.137183734385,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen2.5-vl-72b-instruct","source":"arena","metric":"arena_vision_chinese_elo_votes","value":119,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen2.5-vl-72b-instruct","source":"arena","metric":"arena_vision_chinese_elo_interval","value":55.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_vision_chinese_elo","value":1106.2490036670324,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_vision_chinese_elo_votes","value":278,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_vision_chinese_elo_interval","value":36.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4-turbo","source":"arena","metric":"arena_vision_chinese_elo","value":1045.1526237764322,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4-turbo","source":"arena","metric":"arena_vision_chinese_elo_votes","value":937,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4-turbo","source":"arena","metric":"arena_vision_chinese_elo_interval","value":40.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_vision_chinese_elo","value":1033.2847527859115,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_vision_chinese_elo_votes","value":954,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4o-mini-2024-07-18","source":"arena","metric":"arena_vision_chinese_elo_interval","value":38.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_vision_chinese_elo","value":1009.3611678562212,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_vision_chinese_elo_votes","value":186,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4o-2024-08-06","source":"arena","metric":"arena_vision_chinese_elo_interval","value":52.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_vision_ocr_elo","value":1336.9761739715698,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_vision_ocr_elo_votes","value":10497,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_vision_ocr_elo_interval","value":7.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_vision_ocr_elo","value":1333.351557801051,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_vision_ocr_elo_votes","value":3137,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_vision_ocr_elo_interval","value":11.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_vision_ocr_elo","value":1328.8488534900946,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_vision_ocr_elo_votes","value":12218,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_vision_ocr_elo_interval","value":6.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_vision_ocr_elo","value":1327.2105346969008,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_vision_ocr_elo_votes","value":3456,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_vision_ocr_elo_interval","value":10.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_vision_ocr_elo","value":1326.6071147597515,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_vision_ocr_elo_votes","value":16736,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_vision_ocr_elo_interval","value":6.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_vision_ocr_elo","value":1326.37737208282,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_vision_ocr_elo_votes","value":19407,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_vision_ocr_elo_interval","value":6.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_vision_ocr_elo","value":1325.8797841873654,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_vision_ocr_elo_votes","value":2118,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_vision_ocr_elo_interval","value":13.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_vision_ocr_elo","value":1322.3098518735383,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_vision_ocr_elo_votes","value":6896,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_vision_ocr_elo_interval","value":7.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_vision_ocr_elo","value":1321.766264262086,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_vision_ocr_elo_votes","value":3653,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_vision_ocr_elo_interval","value":10.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_vision_ocr_elo","value":1319.143812885201,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_vision_ocr_elo_votes","value":3701,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_vision_ocr_elo_interval","value":10.36,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_vision_ocr_elo","value":1316.6326678758305,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_vision_ocr_elo_votes","value":9712,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_vision_ocr_elo_interval","value":7.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_vision_ocr_elo","value":1312.7508021712206,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_vision_ocr_elo_votes","value":1343,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_vision_ocr_elo_interval","value":16.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_vision_ocr_elo","value":1311.6349891589696,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_vision_ocr_elo_votes","value":21790,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_vision_ocr_elo_interval","value":5.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_vision_ocr_elo","value":1311.5822655395593,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_vision_ocr_elo_votes","value":6075,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_vision_ocr_elo_interval","value":8.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_vision_ocr_elo","value":1306.0409869668513,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_vision_ocr_elo_votes","value":20286,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_vision_ocr_elo_interval","value":5.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_vision_ocr_elo","value":1303.5654298960042,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_vision_ocr_elo_votes","value":32719,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_vision_ocr_elo_interval","value":4.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_vision_ocr_elo","value":1302.756836568892,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_vision_ocr_elo_votes","value":12994,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_vision_ocr_elo_interval","value":6.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_vision_ocr_elo","value":1301.1680533742315,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_vision_ocr_elo_votes","value":8699,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_vision_ocr_elo_interval","value":7.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_vision_ocr_elo","value":1299.36195628131,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_vision_ocr_elo_votes","value":11021,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_vision_ocr_elo_interval","value":6.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_vision_ocr_elo","value":1296.5213417503217,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_vision_ocr_elo_votes","value":1780,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_vision_ocr_elo_interval","value":14.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_vision_ocr_elo","value":1295.739329120542,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_vision_ocr_elo_votes","value":19839,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_vision_ocr_elo_interval","value":6.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_vision_ocr_elo","value":1292.713382292903,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_vision_ocr_elo_votes","value":8562,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_vision_ocr_elo_interval","value":7.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-astra","source":"arena","metric":"arena_vision_ocr_elo","value":1291.9232352489832,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-astra","source":"arena","metric":"arena_vision_ocr_elo_votes","value":2740,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-astra","source":"arena","metric":"arena_vision_ocr_elo_interval","value":11.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_vision_ocr_elo","value":1291.0883645136398,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_vision_ocr_elo_votes","value":11758,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_vision_ocr_elo_interval","value":7.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_vision_ocr_elo","value":1290.0492120403608,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_vision_ocr_elo_votes","value":7710,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_vision_ocr_elo_interval","value":7.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6.1-sol","source":"arena","metric":"arena_vision_ocr_elo","value":1288.843178996039,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6.1-sol","source":"arena","metric":"arena_vision_ocr_elo_votes","value":1654,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6.1-sol","source":"arena","metric":"arena_vision_ocr_elo_interval","value":14.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_vision_ocr_elo","value":1288.4890609386966,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_vision_ocr_elo_votes","value":9923,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_vision_ocr_elo_interval","value":6.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_vision_ocr_elo","value":1287.6201190163122,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_vision_ocr_elo_votes","value":9827,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_vision_ocr_elo_interval","value":7.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_vision_ocr_elo","value":1284.3598354819687,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_vision_ocr_elo_votes","value":671,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_vision_ocr_elo_interval","value":23.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"arena","metric":"arena_vision_ocr_elo","value":1282.062295454143,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"arena","metric":"arena_vision_ocr_elo_votes","value":2786,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"arena","metric":"arena_vision_ocr_elo_interval","value":11.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_vision_ocr_elo","value":1282.0568798452775,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_vision_ocr_elo_votes","value":1102,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_vision_ocr_elo_interval","value":17.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_vision_ocr_elo","value":1281.9356431353556,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_vision_ocr_elo_votes","value":28054,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_vision_ocr_elo_interval","value":5.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_vision_ocr_elo","value":1280.7667184727638,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_vision_ocr_elo_votes","value":5124,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_vision_ocr_elo_interval","value":9.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_vision_ocr_elo","value":1280.2426591436636,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_vision_ocr_elo_votes","value":6262,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_vision_ocr_elo_interval","value":8.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_vision_ocr_elo","value":1278.006672776666,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_vision_ocr_elo_votes","value":8104,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_vision_ocr_elo_interval","value":7.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_vision_ocr_elo","value":1276.1371934819128,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_vision_ocr_elo_votes","value":19489,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_vision_ocr_elo_interval","value":5.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_vision_ocr_elo","value":1271.8155627984966,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_vision_ocr_elo_votes","value":4881,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_vision_ocr_elo_interval","value":9.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_vision_ocr_elo","value":1270.5023178691142,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_vision_ocr_elo_votes","value":22696,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_vision_ocr_elo_interval","value":5.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_vision_ocr_elo","value":1270.3670553491884,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_vision_ocr_elo_votes","value":32875,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_vision_ocr_elo_interval","value":4.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_vision_ocr_elo","value":1270.1980572999526,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_vision_ocr_elo_votes","value":30138,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_vision_ocr_elo_interval","value":5.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_vision_ocr_elo","value":1270.0034996968593,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_vision_ocr_elo_votes","value":2504,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_vision_ocr_elo_interval","value":12.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_vision_ocr_elo","value":1269.8140484419898,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_vision_ocr_elo_votes","value":1195,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_vision_ocr_elo_interval","value":17.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_vision_ocr_elo","value":1267.7383127469063,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_vision_ocr_elo_votes","value":16862,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_vision_ocr_elo_interval","value":6.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_vision_ocr_elo","value":1264.13695216732,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_vision_ocr_elo_votes","value":7472,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_vision_ocr_elo_interval","value":7.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_vision_ocr_elo","value":1258.5648495261528,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_vision_ocr_elo_votes","value":13947,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_vision_ocr_elo_interval","value":6.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-sol","source":"arena","metric":"arena_vision_ocr_elo","value":1257.8479042328988,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-sol","source":"arena","metric":"arena_vision_ocr_elo_votes","value":2285,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-sol","source":"arena","metric":"arena_vision_ocr_elo_interval","value":12.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_vision_ocr_elo","value":1256.9110095107055,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_vision_ocr_elo_votes","value":12905,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_vision_ocr_elo_interval","value":6.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_vision_ocr_elo","value":1255.8822233146077,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_vision_ocr_elo_votes","value":20901,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_vision_ocr_elo_interval","value":5.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_vision_ocr_elo","value":1255.1000241772645,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_vision_ocr_elo_votes","value":6005,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_vision_ocr_elo_interval","value":8.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_vision_ocr_elo","value":1252.7795555717641,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_vision_ocr_elo_votes","value":18272,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_vision_ocr_elo_interval","value":6.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_vision_ocr_elo","value":1252.6126634511515,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_vision_ocr_elo_votes","value":7752,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_vision_ocr_elo_interval","value":7.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_vision_ocr_elo","value":1250.8253949502591,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_vision_ocr_elo_votes","value":9185,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_vision_ocr_elo_interval","value":7.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_vision_ocr_elo","value":1245.9444871435232,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_vision_ocr_elo_votes","value":19353,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_vision_ocr_elo_interval","value":5.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_vision_ocr_elo","value":1245.716230512117,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_vision_ocr_elo_votes","value":10674,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_vision_ocr_elo_interval","value":9.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_vision_ocr_elo","value":1245.7131112320042,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_vision_ocr_elo_votes","value":21340,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_vision_ocr_elo_interval","value":5.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_vision_ocr_elo","value":1242.90559236893,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_vision_ocr_elo_votes","value":5655,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_vision_ocr_elo_interval","value":8.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_vision_ocr_elo","value":1241.319529524689,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_vision_ocr_elo_votes","value":2508,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_vision_ocr_elo_interval","value":12.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_vision_ocr_elo","value":1237.4596876947876,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_vision_ocr_elo_votes","value":27156,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_vision_ocr_elo_interval","value":4.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_vision_ocr_elo","value":1235.0830964273362,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_vision_ocr_elo_votes","value":19659,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_vision_ocr_elo_interval","value":5.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_vision_ocr_elo","value":1232.703226529258,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_vision_ocr_elo_votes","value":3905,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_vision_ocr_elo_interval","value":10.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-luna","source":"arena","metric":"arena_vision_ocr_elo","value":1224.71622839308,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-luna","source":"arena","metric":"arena_vision_ocr_elo_votes","value":2489,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-luna","source":"arena","metric":"arena_vision_ocr_elo_interval","value":12.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o3","source":"arena","metric":"arena_vision_ocr_elo","value":1218.2761715583013,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o3","source":"arena","metric":"arena_vision_ocr_elo_votes","value":14380,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o3","source":"arena","metric":"arena_vision_ocr_elo_interval","value":8.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_vision_ocr_elo","value":1218.0771206250058,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_vision_ocr_elo_votes","value":11355,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_vision_ocr_elo_interval","value":8.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_vision_ocr_elo","value":1203.791846970892,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_vision_ocr_elo_votes","value":18222,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_vision_ocr_elo_interval","value":6.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_vision_ocr_elo","value":1198.569579963165,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_vision_ocr_elo_votes","value":7999,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_vision_ocr_elo_interval","value":10.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_vision_ocr_elo","value":1196.806679933823,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_vision_ocr_elo_votes","value":11774,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_vision_ocr_elo_interval","value":8.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_vision_ocr_elo","value":1187.51618082674,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_vision_ocr_elo_votes","value":10464,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_vision_ocr_elo_interval","value":9.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3.1","source":"arena","metric":"arena_vision_ocr_elo","value":1174.7143062787038,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3.1","source":"arena","metric":"arena_vision_ocr_elo_votes","value":13469,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3.1","source":"arena","metric":"arena_vision_ocr_elo_interval","value":7.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_vision_ocr_elo","value":1170.8227079327582,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_vision_ocr_elo_votes","value":1484,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_vision_ocr_elo_interval","value":16.27,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_vision_ocr_elo","value":1156.2739576246106,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_vision_ocr_elo_votes","value":6196,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_vision_ocr_elo_interval","value":9.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3","source":"arena","metric":"arena_vision_ocr_elo","value":1154.1060261395198,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3","source":"arena","metric":"arena_vision_ocr_elo_votes","value":4562,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3","source":"arena","metric":"arena_vision_ocr_elo_interval","value":10.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_vision_ocr_elo","value":1152.0542993728461,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_vision_ocr_elo_votes","value":1673,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_vision_ocr_elo_interval","value":15.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_vision_ocr_elo","value":1150.8309638636197,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_vision_ocr_elo_votes","value":1195,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_vision_ocr_elo_interval","value":16.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_vision_ocr_elo","value":1142.9432053739358,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_vision_ocr_elo_votes","value":3083,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_vision_ocr_elo_interval","value":11.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_vision_ocr_elo","value":1131.6968694488453,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_vision_ocr_elo_votes","value":7209,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_vision_ocr_elo_interval","value":10.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_vision_ocr_elo","value":1116.7148618356043,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_vision_ocr_elo_votes","value":2788,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_vision_ocr_elo_interval","value":12.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_vision_diagram_elo","value":1356.7016032221063,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_vision_diagram_elo_votes","value":3956,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_vision_diagram_elo_interval","value":10.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_vision_diagram_elo","value":1347.8434171305662,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_vision_diagram_elo_votes","value":4520,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_vision_diagram_elo_interval","value":9.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_vision_diagram_elo","value":1344.9631052045575,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_vision_diagram_elo_votes","value":711,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_vision_diagram_elo_interval","value":22.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_vision_diagram_elo","value":1344.9206563807784,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_vision_diagram_elo_votes","value":1159,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_vision_diagram_elo_interval","value":18.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_vision_diagram_elo","value":1342.9580501299215,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_vision_diagram_elo_votes","value":1179,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_vision_diagram_elo_interval","value":17.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_vision_diagram_elo","value":1339.7006416302447,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_vision_diagram_elo_votes","value":7249,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_vision_diagram_elo_interval","value":8.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_vision_diagram_elo","value":1335.7379373364147,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_vision_diagram_elo_votes","value":6240,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_vision_diagram_elo_interval","value":9.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_vision_diagram_elo","value":1330.2760181316016,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_vision_diagram_elo_votes","value":1352,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_vision_diagram_elo_interval","value":16.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_vision_diagram_elo","value":1329.1071422962486,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_vision_diagram_elo_votes","value":1364,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_vision_diagram_elo_interval","value":16.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_vision_diagram_elo","value":1328.859134587692,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_vision_diagram_elo_votes","value":625,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_vision_diagram_elo_interval","value":24.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_vision_diagram_elo","value":1326.977878341385,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_vision_diagram_elo_votes","value":8230,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_vision_diagram_elo_interval","value":8.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_vision_diagram_elo","value":1324.9423499186464,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_vision_diagram_elo_votes","value":7798,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_vision_diagram_elo_interval","value":8.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_vision_diagram_elo","value":1323.3502047653537,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_vision_diagram_elo_votes","value":3618,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_vision_diagram_elo_interval","value":10.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_vision_diagram_elo","value":1323.0499663498776,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_vision_diagram_elo_votes","value":2497,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_vision_diagram_elo_interval","value":12.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_vision_diagram_elo","value":1316.9697061160346,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_vision_diagram_elo_votes","value":3995,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_vision_diagram_elo_interval","value":10.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_vision_diagram_elo","value":1316.6840275271343,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_vision_diagram_elo_votes","value":544,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.2","source":"arena","metric":"arena_vision_diagram_elo_interval","value":26.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_vision_diagram_elo","value":1315.1715193796426,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_vision_diagram_elo_votes","value":4883,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_vision_diagram_elo_interval","value":9.52,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_vision_diagram_elo","value":1313.9011098032774,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_vision_diagram_elo_votes","value":2285,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_vision_diagram_elo_interval","value":12.89,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_vision_diagram_elo","value":1310.5356994499275,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_vision_diagram_elo_votes","value":12416,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_vision_diagram_elo_interval","value":6.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_vision_diagram_elo","value":1307.7041122784144,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_vision_diagram_elo_votes","value":423,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_vision_diagram_elo_interval","value":28.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_vision_diagram_elo","value":1305.7347657226037,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_vision_diagram_elo_votes","value":7630,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_vision_diagram_elo_interval","value":8.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6.1-sol","source":"arena","metric":"arena_vision_diagram_elo","value":1305.6606155346667,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6.1-sol","source":"arena","metric":"arena_vision_diagram_elo_votes","value":573,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6.1-sol","source":"arena","metric":"arena_vision_diagram_elo_interval","value":24.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_vision_diagram_elo","value":1305.408603875629,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_vision_diagram_elo_votes","value":2880,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_vision_diagram_elo_interval","value":11.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_vision_diagram_elo","value":1305.0491062492251,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_vision_diagram_elo_votes","value":3340,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_vision_diagram_elo_interval","value":10.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_vision_diagram_elo","value":1303.711602782983,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_vision_diagram_elo_votes","value":3227,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_vision_diagram_elo_interval","value":11.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_vision_diagram_elo","value":1298.0987228609688,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_vision_diagram_elo_votes","value":4304,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_vision_diagram_elo_interval","value":10.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-astra","source":"arena","metric":"arena_vision_diagram_elo","value":1297.2542545036872,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-astra","source":"arena","metric":"arena_vision_diagram_elo_votes","value":966,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-astra","source":"arena","metric":"arena_vision_diagram_elo_interval","value":19.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"arena","metric":"arena_vision_diagram_elo","value":1297.1115165920555,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"arena","metric":"arena_vision_diagram_elo_votes","value":1085,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"arena","metric":"arena_vision_diagram_elo_interval","value":18.6,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_vision_diagram_elo","value":1295.090472283618,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_vision_diagram_elo_votes","value":3090,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_vision_diagram_elo_interval","value":11.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_vision_diagram_elo","value":1292.586620701603,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_vision_diagram_elo_votes","value":3718,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_vision_diagram_elo_interval","value":10.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_vision_diagram_elo","value":1291.6390656297049,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_vision_diagram_elo_votes","value":3752,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_vision_diagram_elo_interval","value":10.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_vision_diagram_elo","value":1287.8420659400235,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_vision_diagram_elo_votes","value":243,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-large-4-0","source":"arena","metric":"arena_vision_diagram_elo_interval","value":37.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_vision_diagram_elo","value":1285.5273468026462,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_vision_diagram_elo_votes","value":11284,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_vision_diagram_elo_interval","value":7.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_vision_diagram_elo","value":1285.2589299934152,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_vision_diagram_elo_votes","value":1838,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_vision_diagram_elo_interval","value":14.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_vision_diagram_elo","value":1284.5527732317032,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_vision_diagram_elo_votes","value":1863,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_vision_diagram_elo_interval","value":14.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_vision_diagram_elo","value":1283.8288258104262,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_vision_diagram_elo_votes","value":2334,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_vision_diagram_elo_interval","value":12.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_vision_diagram_elo","value":1282.519291319008,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_vision_diagram_elo_votes","value":10238,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_vision_diagram_elo_interval","value":7.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_vision_diagram_elo","value":1281.9878180525113,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_vision_diagram_elo_votes","value":7385,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_vision_diagram_elo_interval","value":7.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_vision_diagram_elo","value":1280.751817913318,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_vision_diagram_elo_votes","value":473,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_vision_diagram_elo_interval","value":27.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_vision_diagram_elo","value":1276.8390543564187,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_vision_diagram_elo_votes","value":8623,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_vision_diagram_elo_interval","value":7.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_vision_diagram_elo","value":1276.163173436154,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_vision_diagram_elo_votes","value":919,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_vision_diagram_elo_interval","value":19.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_vision_diagram_elo","value":1273.630980010898,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_vision_diagram_elo_votes","value":9768,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_vision_diagram_elo_interval","value":7.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_vision_diagram_elo","value":1272.6480571654067,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_vision_diagram_elo_votes","value":2789,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_vision_diagram_elo_interval","value":11.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-sol","source":"arena","metric":"arena_vision_diagram_elo","value":1269.5347430048378,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-sol","source":"arena","metric":"arena_vision_diagram_elo_votes","value":844,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-sol","source":"arena","metric":"arena_vision_diagram_elo_interval","value":20.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_vision_diagram_elo","value":1268.7848776023143,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_vision_diagram_elo_votes","value":7723,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_vision_diagram_elo_interval","value":8.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_vision_diagram_elo","value":1266.3634268403093,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_vision_diagram_elo_votes","value":5289,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_vision_diagram_elo_interval","value":9.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_vision_diagram_elo","value":1265.5216639644314,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_vision_diagram_elo_votes","value":6940,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_vision_diagram_elo_interval","value":8.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_vision_diagram_elo","value":1265.4406175506524,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_vision_diagram_elo_votes","value":4773,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_vision_diagram_elo_interval","value":9.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_vision_diagram_elo","value":1264.478751181118,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_vision_diagram_elo_votes","value":2263,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_vision_diagram_elo_interval","value":12.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_vision_diagram_elo","value":1263.7892704874084,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_vision_diagram_elo_votes","value":6239,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_vision_diagram_elo_interval","value":8.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_vision_diagram_elo","value":1255.4179789453528,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_vision_diagram_elo_votes","value":2727,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_vision_diagram_elo_interval","value":11.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_vision_diagram_elo","value":1254.4243279944853,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_vision_diagram_elo_votes","value":938,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_vision_diagram_elo_interval","value":19.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_vision_diagram_elo","value":1253.7673038170278,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_vision_diagram_elo_votes","value":1538,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_vision_diagram_elo_interval","value":16.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_vision_diagram_elo","value":1251.9710450615064,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_vision_diagram_elo_votes","value":2522,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_vision_diagram_elo_interval","value":13.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_vision_diagram_elo","value":1250.7247744665733,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_vision_diagram_elo_votes","value":2071,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_vision_diagram_elo_interval","value":13.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_vision_diagram_elo","value":1249.4884876560818,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_vision_diagram_elo_votes","value":3455,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_vision_diagram_elo_interval","value":10.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_vision_diagram_elo","value":1249.165565796517,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_vision_diagram_elo_votes","value":7927,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_vision_diagram_elo_interval","value":7.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-luna","source":"arena","metric":"arena_vision_diagram_elo","value":1245.347416839249,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-luna","source":"arena","metric":"arena_vision_diagram_elo_votes","value":905,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-luna","source":"arena","metric":"arena_vision_diagram_elo_interval","value":20.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_vision_diagram_elo","value":1245.1824002700137,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_vision_diagram_elo_votes","value":8547,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_vision_diagram_elo_interval","value":7.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_vision_diagram_elo","value":1241.941175017593,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_vision_diagram_elo_votes","value":7269,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_vision_diagram_elo_interval","value":8.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_vision_diagram_elo","value":1240.5400391706717,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_vision_diagram_elo_votes","value":7408,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_vision_diagram_elo_interval","value":8.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o3","source":"arena","metric":"arena_vision_diagram_elo","value":1219.5436552885953,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o3","source":"arena","metric":"arena_vision_diagram_elo_votes","value":3574,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o3","source":"arena","metric":"arena_vision_diagram_elo_interval","value":12.07,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_vision_diagram_elo","value":1214.8624545323785,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_vision_diagram_elo_votes","value":2758,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_vision_diagram_elo_interval","value":13.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_vision_diagram_elo","value":1210.465596274396,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_vision_diagram_elo_votes","value":6840,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_vision_diagram_elo_interval","value":8.89,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_vision_diagram_elo","value":1202.2277607917924,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_vision_diagram_elo_votes","value":1936,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_vision_diagram_elo_interval","value":14.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_vision_diagram_elo","value":1197.054790395398,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_vision_diagram_elo_votes","value":2826,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_vision_diagram_elo_interval","value":12.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_vision_diagram_elo","value":1182.4982883281646,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_vision_diagram_elo_votes","value":578,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_vision_diagram_elo_interval","value":23.4,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_vision_diagram_elo","value":1182.3185194739826,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_vision_diagram_elo_votes","value":2365,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_vision_diagram_elo_interval","value":13.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3.1","source":"arena","metric":"arena_vision_diagram_elo","value":1174.657165110396,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3.1","source":"arena","metric":"arena_vision_diagram_elo_votes","value":3741,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3.1","source":"arena","metric":"arena_vision_diagram_elo_interval","value":10.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_vision_diagram_elo","value":1155.7942444275386,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_vision_diagram_elo_votes","value":1715,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_vision_diagram_elo_interval","value":15.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3","source":"arena","metric":"arena_vision_diagram_elo","value":1155.3892382078252,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3","source":"arena","metric":"arena_vision_diagram_elo_votes","value":1423,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3","source":"arena","metric":"arena_vision_diagram_elo_interval","value":15.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_vision_diagram_elo","value":1151.0274250487262,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_vision_diagram_elo_votes","value":369,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_vision_diagram_elo_interval","value":29.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_vision_diagram_elo","value":1140.5587971317805,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_vision_diagram_elo_votes","value":518,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_vision_diagram_elo_interval","value":26.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_vision_diagram_elo","value":1133.5211210518692,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_vision_diagram_elo_votes","value":947,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_vision_diagram_elo_interval","value":19.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_vision_diagram_elo","value":1125.3066435395635,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_vision_diagram_elo_votes","value":845,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_vision_diagram_elo_interval","value":20.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_vision_diagram_elo","value":1119.498323386029,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_vision_diagram_elo_votes","value":1627,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_vision_diagram_elo_interval","value":15.83,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_vision_homework_elo","value":1362.078523439631,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_vision_homework_elo_votes","value":422,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_vision_homework_elo_interval","value":29.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_vision_homework_elo","value":1360.8653440294418,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_vision_homework_elo_votes","value":1751,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_vision_homework_elo_interval","value":14.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6.1-sol","source":"arena","metric":"arena_vision_homework_elo","value":1355.605381138743,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6.1-sol","source":"arena","metric":"arena_vision_homework_elo_votes","value":368,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6.1-sol","source":"arena","metric":"arena_vision_homework_elo_interval","value":31.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_vision_homework_elo","value":1351.4553178215317,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_vision_homework_elo_votes","value":681,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_vision_homework_elo_interval","value":22.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_vision_homework_elo","value":1345.2298506834072,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_vision_homework_elo_votes","value":756,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_vision_homework_elo_interval","value":21.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_vision_homework_elo","value":1337.5687243848406,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_vision_homework_elo_votes","value":1899,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_vision_homework_elo_interval","value":14.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-astra","source":"arena","metric":"arena_vision_homework_elo","value":1337.4727595950876,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-astra","source":"arena","metric":"arena_vision_homework_elo_votes","value":560,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-astra","source":"arena","metric":"arena_vision_homework_elo_interval","value":24.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_vision_homework_elo","value":1337.3951065152785,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_vision_homework_elo_votes","value":3084,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_vision_homework_elo_interval","value":11.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_vision_homework_elo","value":1336.8077467869628,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_vision_homework_elo_votes","value":2077,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_vision_homework_elo_interval","value":13.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_vision_homework_elo","value":1336.7445364508553,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_vision_homework_elo_votes","value":2845,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_vision_homework_elo_interval","value":11.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_vision_homework_elo","value":1335.9297440602643,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_vision_homework_elo_votes","value":4003,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_vision_homework_elo_interval","value":10.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_vision_homework_elo","value":1335.6470255442944,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_vision_homework_elo_votes","value":909,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_vision_homework_elo_interval","value":19.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_vision_homework_elo","value":1331.7730759290296,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_vision_homework_elo_votes","value":3535,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_vision_homework_elo_interval","value":10.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_vision_homework_elo","value":1331.0948790498433,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_vision_homework_elo_votes","value":395,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_vision_homework_elo_interval","value":29.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_vision_homework_elo","value":1329.887436500181,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_vision_homework_elo_votes","value":1553,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_vision_homework_elo_interval","value":15.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_vision_homework_elo","value":1319.9898099139846,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_vision_homework_elo_votes","value":665,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_vision_homework_elo_interval","value":22.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_vision_homework_elo","value":1317.7628804429905,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_vision_homework_elo_votes","value":2229,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_vision_homework_elo_interval","value":12.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_vision_homework_elo","value":1316.245485827796,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_vision_homework_elo_votes","value":6293,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_vision_homework_elo_interval","value":8.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_vision_homework_elo","value":1313.7704490528347,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_vision_homework_elo_votes","value":993,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_vision_homework_elo_interval","value":18.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_vision_homework_elo","value":1312.097216222971,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_vision_homework_elo_votes","value":1286,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_vision_homework_elo_interval","value":16.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_vision_homework_elo","value":1311.2338701811398,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_vision_homework_elo_votes","value":3700,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_vision_homework_elo_interval","value":10.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_vision_homework_elo","value":1311.0466924142092,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_vision_homework_elo_votes","value":1500,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_vision_homework_elo_interval","value":15.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_vision_homework_elo","value":1309.727806038155,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_vision_homework_elo_votes","value":2263,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_vision_homework_elo_interval","value":12.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_vision_homework_elo","value":1309.7138518451425,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_vision_homework_elo_votes","value":6435,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_vision_homework_elo_interval","value":8.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_vision_homework_elo","value":1309.0220230605871,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_vision_homework_elo_votes","value":517,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_vision_homework_elo_interval","value":25.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"arena","metric":"arena_vision_homework_elo","value":1306.6980316785766,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"arena","metric":"arena_vision_homework_elo_votes","value":521,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"arena","metric":"arena_vision_homework_elo_interval","value":25.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_vision_homework_elo","value":1304.5140829363736,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_vision_homework_elo_votes","value":1190,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_vision_homework_elo_interval","value":17.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_vision_homework_elo","value":1296.653374592549,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_vision_homework_elo_votes","value":3649,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_vision_homework_elo_interval","value":10.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_vision_homework_elo","value":1296.2007277606715,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_vision_homework_elo_votes","value":680,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_vision_homework_elo_interval","value":22.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_vision_homework_elo","value":1295.4797131426467,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_vision_homework_elo_votes","value":1284,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_vision_homework_elo_interval","value":17.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_vision_homework_elo","value":1294.7266778637306,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_vision_homework_elo_votes","value":1646,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_vision_homework_elo_interval","value":14.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_vision_homework_elo","value":1294.7086381362935,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_vision_homework_elo_votes","value":919,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_vision_homework_elo_interval","value":19.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_vision_homework_elo","value":1293.3058195769715,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_vision_homework_elo_votes","value":3822,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_vision_homework_elo_interval","value":10.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_vision_homework_elo","value":1292.424899438349,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_vision_homework_elo_votes","value":4001,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_vision_homework_elo_interval","value":9.66,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_vision_homework_elo","value":1290.905617836861,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_vision_homework_elo_votes","value":1010,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_vision_homework_elo_interval","value":19.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_vision_homework_elo","value":1286.9325882572148,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_vision_homework_elo_votes","value":1354,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_vision_homework_elo_interval","value":16.17,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-sol","source":"arena","metric":"arena_vision_homework_elo","value":1286.34636227072,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-sol","source":"arena","metric":"arena_vision_homework_elo_votes","value":518,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-sol","source":"arena","metric":"arena_vision_homework_elo_interval","value":25.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_vision_homework_elo","value":1285.4874661689778,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_vision_homework_elo_votes","value":3492,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_vision_homework_elo_interval","value":10.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_vision_homework_elo","value":1283.2338342439402,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_vision_homework_elo_votes","value":873,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_vision_homework_elo_interval","value":19.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_vision_homework_elo","value":1282.9434202384296,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_vision_homework_elo_votes","value":546,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_vision_homework_elo_interval","value":25.59,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_vision_homework_elo","value":1282.4460001218517,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_vision_homework_elo_votes","value":1128,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_vision_homework_elo_interval","value":18.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_vision_homework_elo","value":1280.5538481724927,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_vision_homework_elo_votes","value":5415,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_vision_homework_elo_interval","value":8.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_vision_homework_elo","value":1278.460465855433,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_vision_homework_elo_votes","value":1325,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_vision_homework_elo_interval","value":16.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_vision_homework_elo","value":1276.6308252187878,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_vision_homework_elo_votes","value":1611,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_vision_homework_elo_interval","value":14.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_vision_homework_elo","value":1276.2416679020682,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_vision_homework_elo_votes","value":2888,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_vision_homework_elo_interval","value":11.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_vision_homework_elo","value":1273.336859476231,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_vision_homework_elo_votes","value":5226,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_vision_homework_elo_interval","value":9.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_vision_homework_elo","value":1271.793791343327,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_vision_homework_elo_votes","value":1218,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_vision_homework_elo_interval","value":16.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_vision_homework_elo","value":1270.6873783933054,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_vision_homework_elo_votes","value":3947,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_vision_homework_elo_interval","value":10.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_vision_homework_elo","value":1268.022728144441,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_vision_homework_elo_votes","value":2405,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_vision_homework_elo_interval","value":12.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_vision_homework_elo","value":1265.2969229847035,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_vision_homework_elo_votes","value":233,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"stepfun/step-5-preview","source":"arena","metric":"arena_vision_homework_elo_interval","value":37.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_vision_homework_elo","value":1264.2457578229214,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_vision_homework_elo_votes","value":226,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"arena","metric":"arena_vision_homework_elo_interval","value":39.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_vision_homework_elo","value":1261.5753619645998,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_vision_homework_elo_votes","value":4076,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_vision_homework_elo_interval","value":10.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_vision_homework_elo","value":1260.969122141075,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_vision_homework_elo_votes","value":1929,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_vision_homework_elo_interval","value":13.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-luna","source":"arena","metric":"arena_vision_homework_elo","value":1260.8829292206838,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-luna","source":"arena","metric":"arena_vision_homework_elo_votes","value":550,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-luna","source":"arena","metric":"arena_vision_homework_elo_interval","value":25.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_vision_homework_elo","value":1257.4392690774348,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_vision_homework_elo_votes","value":835,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_vision_homework_elo_interval","value":20.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_vision_homework_elo","value":1256.2163855444346,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_vision_homework_elo_votes","value":3843,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_vision_homework_elo_interval","value":9.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_vision_homework_elo","value":1248.4401715305896,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_vision_homework_elo_votes","value":1478,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_vision_homework_elo_interval","value":16.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_vision_homework_elo","value":1244.3468732584847,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_vision_homework_elo_votes","value":4863,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_vision_homework_elo_interval","value":9.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_vision_homework_elo","value":1241.2203611589446,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_vision_homework_elo_votes","value":3560,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_vision_homework_elo_interval","value":10.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_vision_homework_elo","value":1234.229620949634,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_vision_homework_elo_votes","value":1588,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_vision_homework_elo_interval","value":16.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o3","source":"arena","metric":"arena_vision_homework_elo","value":1233.9830320874212,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o3","source":"arena","metric":"arena_vision_homework_elo_votes","value":1930,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o3","source":"arena","metric":"arena_vision_homework_elo_interval","value":14.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_vision_homework_elo","value":1229.5313614279073,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_vision_homework_elo_votes","value":803,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_vision_homework_elo_interval","value":22.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_vision_homework_elo","value":1225.1445802590279,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_vision_homework_elo_votes","value":3429,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_vision_homework_elo_interval","value":11.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_vision_homework_elo","value":1213.5079400423606,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_vision_homework_elo_votes","value":1310,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_vision_homework_elo_interval","value":17.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_vision_homework_elo","value":1209.7424578800046,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_vision_homework_elo_votes","value":976,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_vision_homework_elo_interval","value":19.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3.1","source":"arena","metric":"arena_vision_homework_elo","value":1165.399875785219,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3.1","source":"arena","metric":"arena_vision_homework_elo_votes","value":2146,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3.1","source":"arena","metric":"arena_vision_homework_elo_interval","value":13.36,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3","source":"arena","metric":"arena_vision_homework_elo","value":1165.343173810586,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3","source":"arena","metric":"arena_vision_homework_elo_votes","value":809,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3","source":"arena","metric":"arena_vision_homework_elo_interval","value":20.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_vision_homework_elo","value":1164.1770917372469,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_vision_homework_elo_votes","value":526,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_vision_homework_elo_interval","value":25.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_vision_homework_elo","value":1162.7426344013825,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_vision_homework_elo_votes","value":215,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.5v","source":"arena","metric":"arena_vision_homework_elo_interval","value":38.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_vision_homework_elo","value":1159.7779975930737,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_vision_homework_elo_votes","value":1034,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_vision_homework_elo_interval","value":18.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_vision_homework_elo","value":1157.8966631825842,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_vision_homework_elo_votes","value":809,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_vision_homework_elo_interval","value":21.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_vision_homework_elo","value":1157.4851204020556,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_vision_homework_elo_votes","value":260,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_vision_homework_elo_interval","value":34.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_vision_homework_elo","value":1155.3571900450193,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_vision_homework_elo_votes","value":271,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_vision_homework_elo_interval","value":36.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_vision_homework_elo","value":1148.0631782736937,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_vision_homework_elo_votes","value":477,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_vision_homework_elo_interval","value":26.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_vision_humor_elo","value":1340.7234971433068,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_vision_humor_elo_votes","value":583,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_vision_humor_elo_interval","value":25.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_vision_humor_elo","value":1322.3917899316255,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_vision_humor_elo_votes","value":1885,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_vision_humor_elo_interval","value":14.21,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_vision_humor_elo","value":1321.3855700046079,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_vision_humor_elo_votes","value":577,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_vision_humor_elo_interval","value":25.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_vision_humor_elo","value":1320.978439946774,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_vision_humor_elo_votes","value":175,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_vision_humor_elo_interval","value":45.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_vision_humor_elo","value":1317.861423655431,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_vision_humor_elo_votes","value":208,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_vision_humor_elo_interval","value":40.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_vision_humor_elo","value":1313.8101821701612,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_vision_humor_elo_votes","value":1026,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_vision_humor_elo_interval","value":19.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_vision_humor_elo","value":1309.3853121478735,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_vision_humor_elo_votes","value":889,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_vision_humor_elo_interval","value":20.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_vision_humor_elo","value":1304.471331887602,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_vision_humor_elo_votes","value":435,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_vision_humor_elo_interval","value":29.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_vision_humor_elo","value":1299.3830404298008,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_vision_humor_elo_votes","value":215,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_vision_humor_elo_interval","value":41.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_vision_humor_elo","value":1293.27180989201,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_vision_humor_elo_votes","value":876,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_vision_humor_elo_interval","value":20.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_vision_humor_elo","value":1292.806015704831,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_vision_humor_elo_votes","value":208,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_vision_humor_elo_interval","value":41.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_vision_humor_elo","value":1292.694995989837,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_vision_humor_elo_votes","value":1075,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_vision_humor_elo_interval","value":18.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_vision_humor_elo","value":1288.8567768806597,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_vision_humor_elo_votes","value":427,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_vision_humor_elo_interval","value":29.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_vision_humor_elo","value":1288.4986287644438,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_vision_humor_elo_votes","value":577,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_vision_humor_elo_interval","value":25.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_vision_humor_elo","value":1286.703179126294,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_vision_humor_elo_votes","value":396,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_vision_humor_elo_interval","value":29.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_vision_humor_elo","value":1284.0902068421517,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_vision_humor_elo_votes","value":1143,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_vision_humor_elo_interval","value":18.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_vision_humor_elo","value":1283.71131909474,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_vision_humor_elo_votes","value":1083,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_vision_humor_elo_interval","value":18.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_vision_humor_elo","value":1281.6115493825507,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_vision_humor_elo_votes","value":756,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_vision_humor_elo_interval","value":22.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_vision_humor_elo","value":1279.9516022266782,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_vision_humor_elo_votes","value":590,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_vision_humor_elo_interval","value":24.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_vision_humor_elo","value":1279.941896836019,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_vision_humor_elo_votes","value":1659,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_vision_humor_elo_interval","value":14.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_vision_humor_elo","value":1279.2768132900635,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_vision_humor_elo_votes","value":671,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_vision_humor_elo_interval","value":23.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_vision_humor_elo","value":1275.9529271617535,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_vision_humor_elo_votes","value":573,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_vision_humor_elo_interval","value":25.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_vision_humor_elo","value":1272.3017994114443,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_vision_humor_elo_votes","value":993,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_vision_humor_elo_interval","value":19.19,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_vision_humor_elo","value":1270.0548860376123,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_vision_humor_elo_votes","value":320,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_vision_humor_elo_interval","value":32.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_vision_humor_elo","value":1267.5960650478607,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_vision_humor_elo_votes","value":1765,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_vision_humor_elo_interval","value":14.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_vision_humor_elo","value":1265.8626550281565,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_vision_humor_elo_votes","value":979,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_vision_humor_elo_interval","value":19.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_vision_humor_elo","value":1263.1827506782947,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_vision_humor_elo_votes","value":376,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_vision_humor_elo_interval","value":31.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_vision_humor_elo","value":1262.2983398944116,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_vision_humor_elo_votes","value":3133,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_vision_humor_elo_interval","value":14.93,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_vision_humor_elo","value":1261.87693537721,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_vision_humor_elo_votes","value":1223,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_vision_humor_elo_interval","value":17.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_vision_humor_elo","value":1261.2975686245095,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_vision_humor_elo_votes","value":556,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_vision_humor_elo_interval","value":25.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_vision_humor_elo","value":1260.6831353434936,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_vision_humor_elo_votes","value":628,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_vision_humor_elo_interval","value":24.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"arena","metric":"arena_vision_humor_elo","value":1260.2873021211328,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"arena","metric":"arena_vision_humor_elo_votes","value":166,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"arena","metric":"arena_vision_humor_elo_interval","value":45.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_vision_humor_elo","value":1248.363456095546,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_vision_humor_elo_votes","value":1060,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_vision_humor_elo_interval","value":19.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_vision_humor_elo","value":1246.0558510975607,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_vision_humor_elo_votes","value":569,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_vision_humor_elo_interval","value":25.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_vision_humor_elo","value":1243.1671633712667,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_vision_humor_elo_votes","value":468,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_vision_humor_elo_interval","value":27.28,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_vision_humor_elo","value":1236.3145523850667,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_vision_humor_elo_votes","value":526,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_vision_humor_elo_interval","value":26.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_vision_humor_elo","value":1235.4335998920615,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_vision_humor_elo_votes","value":347,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_vision_humor_elo_interval","value":32.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_vision_humor_elo","value":1235.1915609276853,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_vision_humor_elo_votes","value":868,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_vision_humor_elo_interval","value":21.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_vision_humor_elo","value":1235.0297273645444,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_vision_humor_elo_votes","value":773,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_vision_humor_elo_interval","value":22.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_vision_humor_elo","value":1226.9102673475843,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_vision_humor_elo_votes","value":1195,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_vision_humor_elo_interval","value":17.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_vision_humor_elo","value":1226.8331566830793,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_vision_humor_elo_votes","value":681,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_vision_humor_elo_interval","value":23.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_vision_humor_elo","value":1225.8091238959082,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_vision_humor_elo_votes","value":1147,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_vision_humor_elo_interval","value":18.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_vision_humor_elo","value":1225.3999240522392,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_vision_humor_elo_votes","value":2192,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_vision_humor_elo_interval","value":15.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o3","source":"arena","metric":"arena_vision_humor_elo","value":1222.279984248095,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o3","source":"arena","metric":"arena_vision_humor_elo_votes","value":1643,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o3","source":"arena","metric":"arena_vision_humor_elo_interval","value":19.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_vision_humor_elo","value":1221.9594637218295,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_vision_humor_elo_votes","value":1069,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_vision_humor_elo_interval","value":18.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_vision_humor_elo","value":1218.7377753786031,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_vision_humor_elo_votes","value":1448,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_vision_humor_elo_interval","value":20.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_vision_humor_elo","value":1216.4153868404055,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_vision_humor_elo_votes","value":238,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_vision_humor_elo_interval","value":39.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_vision_humor_elo","value":1208.7960192078913,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_vision_humor_elo_votes","value":508,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_vision_humor_elo_interval","value":26.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_vision_humor_elo","value":1207.386214209189,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_vision_humor_elo_votes","value":384,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_vision_humor_elo_interval","value":30.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_vision_humor_elo","value":1205.4902177218778,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_vision_humor_elo_votes","value":1047,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_vision_humor_elo_interval","value":22.45,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_vision_humor_elo","value":1199.4124401698377,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_vision_humor_elo_votes","value":1449,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_vision_humor_elo_interval","value":20.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_vision_humor_elo","value":1195.9398849801314,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_vision_humor_elo_votes","value":1365,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_vision_humor_elo_interval","value":20.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_vision_humor_elo","value":1190.202010098968,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_vision_humor_elo_votes","value":502,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_vision_humor_elo_interval","value":27.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_vision_humor_elo","value":1181.8601359454121,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_vision_humor_elo_votes","value":1403,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_vision_humor_elo_interval","value":20.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3.1","source":"arena","metric":"arena_vision_humor_elo","value":1167.8098259074136,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3.1","source":"arena","metric":"arena_vision_humor_elo_votes","value":1502,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3.1","source":"arena","metric":"arena_vision_humor_elo_interval","value":19.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_vision_humor_elo","value":1166.242332648924,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_vision_humor_elo_votes","value":762,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_vision_humor_elo_interval","value":24.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_vision_humor_elo","value":1161.018972837397,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_vision_humor_elo_votes","value":923,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_vision_humor_elo_interval","value":20.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3","source":"arena","metric":"arena_vision_humor_elo","value":1144.8370799280024,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3","source":"arena","metric":"arena_vision_humor_elo_votes","value":440,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3","source":"arena","metric":"arena_vision_humor_elo_interval","value":30.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_vision_humor_elo","value":1141.8985047385509,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_vision_humor_elo_votes","value":933,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_vision_humor_elo_interval","value":23.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_vision_humor_elo","value":1110.1803741770846,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_vision_humor_elo_votes","value":174,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-nano","source":"arena","metric":"arena_vision_humor_elo_interval","value":46.54,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_vision_humor_elo","value":1101.5604794717256,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_vision_humor_elo_votes","value":191,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_vision_humor_elo_interval","value":44.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_vision_humor_elo","value":1100.0399205814513,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_vision_humor_elo_votes","value":216,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_vision_humor_elo_interval","value":40.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_vision_captioning_elo","value":1344.8857647933394,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_vision_captioning_elo_votes","value":137,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_vision_captioning_elo_interval","value":48.55,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_vision_captioning_elo","value":1303.5663600127425,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_vision_captioning_elo_votes","value":796,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_vision_captioning_elo_interval","value":22.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_vision_captioning_elo","value":1296.7088279820423,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_vision_captioning_elo_votes","value":63,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_vision_captioning_elo_interval","value":69.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_vision_captioning_elo","value":1281.3240583191548,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_vision_captioning_elo_votes","value":146,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_vision_captioning_elo_interval","value":44.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_vision_captioning_elo","value":1276.6460243375493,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_vision_captioning_elo_votes","value":582,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_vision_captioning_elo_interval","value":24.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_vision_captioning_elo","value":1266.6369794940363,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_vision_captioning_elo_votes","value":94,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_vision_captioning_elo_interval","value":57.97,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_vision_captioning_elo","value":1264.162619884503,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_vision_captioning_elo_votes","value":53,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_vision_captioning_elo_interval","value":72.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_vision_captioning_elo","value":1259.4523996474286,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_vision_captioning_elo_votes","value":73,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_vision_captioning_elo_interval","value":64.48,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_vision_captioning_elo","value":1257.127304930356,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_vision_captioning_elo_votes","value":125,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_vision_captioning_elo_interval","value":48.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_vision_captioning_elo","value":1251.6128156563502,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_vision_captioning_elo_votes","value":101,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_vision_captioning_elo_interval","value":55.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_vision_captioning_elo","value":1229.6993078212156,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_vision_captioning_elo_votes","value":78,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_vision_captioning_elo_interval","value":56.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_vision_captioning_elo","value":1217.52490819928,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_vision_captioning_elo_votes","value":106,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_vision_captioning_elo_interval","value":54.11,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_vision_captioning_elo","value":1216.962021342088,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_vision_captioning_elo_votes","value":283,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_vision_captioning_elo_interval","value":36.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_vision_captioning_elo","value":1211.5691736478948,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_vision_captioning_elo_votes","value":375,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_vision_captioning_elo_interval","value":31.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o3","source":"arena","metric":"arena_vision_captioning_elo","value":1209.7409809094365,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o3","source":"arena","metric":"arena_vision_captioning_elo_votes","value":540,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o3","source":"arena","metric":"arena_vision_captioning_elo_interval","value":27.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_vision_captioning_elo","value":1206.7568544586018,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_vision_captioning_elo_votes","value":422,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_vision_captioning_elo_interval","value":31.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_vision_captioning_elo","value":1204.03810994242,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_vision_captioning_elo_votes","value":423,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_vision_captioning_elo_interval","value":29.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_vision_captioning_elo","value":1173.9566121663102,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_vision_captioning_elo_votes","value":394,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_vision_captioning_elo_interval","value":32.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_vision_captioning_elo","value":1170.204176393505,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_vision_captioning_elo_votes","value":61,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_vision_captioning_elo_interval","value":81.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_vision_captioning_elo","value":1152.8906231176825,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_vision_captioning_elo_votes","value":258,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_vision_captioning_elo_interval","value":38.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_vision_captioning_elo","value":1151.1786351856742,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_vision_captioning_elo_votes","value":258,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_vision_captioning_elo_interval","value":38.63,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3.1","source":"arena","metric":"arena_vision_captioning_elo","value":1144.6216401040872,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3.1","source":"arena","metric":"arena_vision_captioning_elo_votes","value":403,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3.1","source":"arena","metric":"arena_vision_captioning_elo_interval","value":30.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3","source":"arena","metric":"arena_vision_captioning_elo","value":1094.2471452643588,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3","source":"arena","metric":"arena_vision_captioning_elo_votes","value":160,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3","source":"arena","metric":"arena_vision_captioning_elo_interval","value":49.23,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_vision_entities_elo","value":1329.7022623203447,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_vision_entities_elo_votes","value":388,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_vision_entities_elo_interval","value":28.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_vision_entities_elo","value":1307.5929948588014,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_vision_entities_elo_votes","value":259,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_vision_entities_elo_interval","value":33.43,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_vision_entities_elo","value":1284.8350740884655,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_vision_entities_elo_votes","value":275,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_vision_entities_elo_interval","value":32.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_vision_entities_elo","value":1283.1608183516266,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_vision_entities_elo_votes","value":917,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_vision_entities_elo_interval","value":22.08,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_vision_entities_elo","value":1277.835367242795,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_vision_entities_elo_votes","value":154,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_vision_entities_elo_interval","value":40.61,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_vision_entities_elo","value":1273.553246408339,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_vision_entities_elo_votes","value":189,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_vision_entities_elo_interval","value":38.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_vision_entities_elo","value":1264.7777075197748,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_vision_entities_elo_votes","value":222,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_vision_entities_elo_interval","value":36.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_vision_entities_elo","value":1262.5809739235285,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_vision_entities_elo_votes","value":432,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_vision_entities_elo_interval","value":30.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_vision_entities_elo","value":1251.6437237658427,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_vision_entities_elo_votes","value":628,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_vision_entities_elo_interval","value":23.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_vision_entities_elo","value":1251.1294095628514,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_vision_entities_elo_votes","value":137,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_vision_entities_elo_interval","value":45.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_vision_entities_elo","value":1248.540528355999,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_vision_entities_elo_votes","value":151,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_vision_entities_elo_interval","value":41.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_vision_entities_elo","value":1241.3475893308646,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_vision_entities_elo_votes","value":231,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_vision_entities_elo_interval","value":38.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o3","source":"arena","metric":"arena_vision_entities_elo","value":1233.82611744309,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o3","source":"arena","metric":"arena_vision_entities_elo_votes","value":494,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o3","source":"arena","metric":"arena_vision_entities_elo_interval","value":29.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_vision_entities_elo","value":1231.964074713659,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_vision_entities_elo_votes","value":168,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_vision_entities_elo_interval","value":41.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_vision_entities_elo","value":1231.8116671913624,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_vision_entities_elo_votes","value":112,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_vision_entities_elo_interval","value":49.35,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_vision_entities_elo","value":1231.2784312744789,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_vision_entities_elo_votes","value":119,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_vision_entities_elo_interval","value":52.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_vision_entities_elo","value":1226.0321800913969,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_vision_entities_elo_votes","value":282,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_vision_entities_elo_interval","value":35.57,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_vision_entities_elo","value":1225.7072113834445,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_vision_entities_elo_votes","value":359,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_vision_entities_elo_interval","value":28.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_vision_entities_elo","value":1218.2159438730218,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_vision_entities_elo_votes","value":183,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_vision_entities_elo_interval","value":40.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_vision_entities_elo","value":1217.8753075858417,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_vision_entities_elo_votes","value":388,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_vision_entities_elo_interval","value":32.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_vision_entities_elo","value":1217.31004159851,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_vision_entities_elo_votes","value":142,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_vision_entities_elo_interval","value":44.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_vision_entities_elo","value":1210.10867267618,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_vision_entities_elo_votes","value":187,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_vision_entities_elo_interval","value":41.06,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_vision_entities_elo","value":1207.530734220722,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_vision_entities_elo_votes","value":392,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_vision_entities_elo_interval","value":32.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_vision_entities_elo","value":1196.7494623815019,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_vision_entities_elo_votes","value":107,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_vision_entities_elo_interval","value":53.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_vision_entities_elo","value":1196.0216482696978,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_vision_entities_elo_votes","value":313,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_vision_entities_elo_interval","value":34.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_vision_entities_elo","value":1195.4717443715072,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_vision_entities_elo_votes","value":162,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_vision_entities_elo_interval","value":45.58,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_vision_entities_elo","value":1190.6465354821917,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_vision_entities_elo_votes","value":235,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_vision_entities_elo_interval","value":36.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_vision_entities_elo","value":1188.6438029996154,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_vision_entities_elo_votes","value":185,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_vision_entities_elo_interval","value":40.32,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_vision_entities_elo","value":1186.84951925224,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_vision_entities_elo_votes","value":357,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_vision_entities_elo_interval","value":32.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_vision_entities_elo","value":1154.7263308805454,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_vision_entities_elo_votes","value":240,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_vision_entities_elo_interval","value":40.79,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3.1","source":"arena","metric":"arena_vision_entities_elo","value":1147.1319205671653,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3.1","source":"arena","metric":"arena_vision_entities_elo_votes","value":439,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3.1","source":"arena","metric":"arena_vision_entities_elo_interval","value":31.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_vision_entities_elo","value":1140.777609977281,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_vision_entities_elo_votes","value":178,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_vision_entities_elo_interval","value":42.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3","source":"arena","metric":"arena_vision_entities_elo","value":1140.6345375534315,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3","source":"arena","metric":"arena_vision_entities_elo_votes","value":200,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3","source":"arena","metric":"arena_vision_entities_elo_interval","value":40.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_vision_creative_writing_elo","value":1337.6994467864388,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":1159,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":18.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_vision_creative_writing_elo","value":1331.3013341521682,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":1407,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":16.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_vision_creative_writing_elo","value":1329.718816913958,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":511,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":28.15,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_vision_creative_writing_elo","value":1325.5695859308173,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":1454,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":16.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_vision_creative_writing_elo","value":1324.1943654824238,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":3296,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":11.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_vision_creative_writing_elo","value":1320.4063143780436,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":283,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":37.36,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_vision_creative_writing_elo","value":1312.9300904816278,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":1633,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":15.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_vision_creative_writing_elo","value":1311.686613995963,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":747,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":22.1,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_vision_creative_writing_elo","value":1311.5314164072163,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":505,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.7-flash","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":27.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_vision_creative_writing_elo","value":1301.3553920419376,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":2038,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":13.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_vision_creative_writing_elo","value":1301.2991080979102,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":1180,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":18.31,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_vision_creative_writing_elo","value":1300.8984870253153,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":1398,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":16.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6.1-sol","source":"arena","metric":"arena_vision_creative_writing_elo","value":1300.664434956268,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6.1-sol","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":229,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6.1-sol","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":39.85,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_vision_creative_writing_elo","value":1299.2677712291568,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":459,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.8-flash","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":28.77,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_vision_creative_writing_elo","value":1295.7025632561022,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":493,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.3","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":27.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_vision_creative_writing_elo","value":1292.690980588118,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":1094,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":19.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-astra","source":"arena","metric":"arena_vision_creative_writing_elo","value":1285.52284379152,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-astra","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":408,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-astra","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":30.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_vision_creative_writing_elo","value":1284.7284902970791,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":2703,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":11.98,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_vision_creative_writing_elo","value":1283.3910817806966,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":1039,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":19.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_vision_creative_writing_elo","value":1283.1180708317,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":2112,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":13.75,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_vision_creative_writing_elo","value":1278.3802439046713,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":792,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":22.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"arena","metric":"arena_vision_creative_writing_elo","value":1274.61195021627,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":345,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":32.94,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_vision_creative_writing_elo","value":1273.2002670287864,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":916,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":20,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_vision_creative_writing_elo","value":1272.3156371362413,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":1696,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":15.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_vision_creative_writing_elo","value":1269.556645853856,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":1355,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5.3-flash","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":16.89,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_vision_creative_writing_elo","value":1268.7803024701839,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":1768,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"moonshotai/kimi-k2.5","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":14.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_vision_creative_writing_elo","value":1266.3542346620727,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":935,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":21.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_vision_creative_writing_elo","value":1264.7158169723175,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":3682,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":12.44,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_vision_creative_writing_elo","value":1262.1281344342392,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":714,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":23.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_vision_creative_writing_elo","value":1260.303354012809,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":2304,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":12.95,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_vision_creative_writing_elo","value":1259.720942975146,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":862,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.5-flash-lite","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":21.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_vision_creative_writing_elo","value":1257.710430064435,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":1094,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":18.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_vision_creative_writing_elo","value":1256.7731301861274,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":977,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":19.92,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_vision_creative_writing_elo","value":1255.752596231603,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":1495,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-4-26b-a4b-it","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":15.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_vision_creative_writing_elo","value":1253.2988293021428,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":1130,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":18.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_vision_creative_writing_elo","value":1251.6963141043723,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":2924,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":11.74,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_vision_creative_writing_elo","value":1248.1033686241062,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":992,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":19.88,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_vision_creative_writing_elo","value":1247.6301911250919,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":1883,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":14.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_vision_creative_writing_elo","value":1245.7364207185008,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":1124,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":18.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_vision_creative_writing_elo","value":1241.8926057951162,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":228,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"anthropic/claude-sonnet-5.5","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":40.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_vision_creative_writing_elo","value":1241.1048298676444,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":2919,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemini-2.5-flash","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":12.65,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_vision_creative_writing_elo","value":1237.0776828992007,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":696,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.8-27b","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":23.16,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_vision_creative_writing_elo","value":1236.569056773464,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":2011,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":14.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_vision_creative_writing_elo","value":1233.6104262364424,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":1339,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":17.03,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_vision_creative_writing_elo","value":1231.3939526187714,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":303,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.6-flash","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":35.81,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_vision_creative_writing_elo","value":1229.9939399917878,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":1908,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"xiaomi/mimo-v2.5","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":14.39,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_vision_creative_writing_elo","value":1224.9582069296887,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":1290,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":17.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_vision_creative_writing_elo","value":1224.197942198075,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":2140,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-27b","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":13.56,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_vision_creative_writing_elo","value":1222.1798615589869,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":1629,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-mini","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":15.47,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_vision_creative_writing_elo","value":1220.3459482699627,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":865,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3.5-122b-a10b","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":20.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_vision_creative_writing_elo","value":1219.9200220426112,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":974,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"qwen/qwen3-vl-235b-a22b-instruct","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":19.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-sol","source":"arena","metric":"arena_vision_creative_writing_elo","value":1218.9198853961523,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-sol","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":286,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-sol","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":37.68,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_vision_creative_writing_elo","value":1217.2146730987201,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":370,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"x-ai/grok-4.7","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":32.53,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_vision_creative_writing_elo","value":1210.1959974624258,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":1297,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":19.38,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_vision_creative_writing_elo","value":1209.970004704274,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":1283,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":19.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-luna","source":"arena","metric":"arena_vision_creative_writing_elo","value":1205.262353867158,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-luna","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":327,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-6-luna","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":34.33,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_vision_creative_writing_elo","value":1205.1626210544894,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":675,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"thinkingmachines/inkling-small","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":23.99,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o3","source":"arena","metric":"arena_vision_creative_writing_elo","value":1201.1419789788933,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o3","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":1584,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o3","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":18.14,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3.1","source":"arena","metric":"arena_vision_creative_writing_elo","value":1199.737035000535,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3.1","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":1550,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3.1","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":17.3,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_vision_creative_writing_elo","value":1197.813898835316,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":343,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3-5","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":33.13,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_vision_creative_writing_elo","value":1182.2993311125972,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":1192,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-4.1-mini","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":20.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_vision_creative_writing_elo","value":1180.9876667372791,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":1017,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5-mini","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":21.49,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_vision_creative_writing_elo","value":1176.8533610635618,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":627,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"google/gemma-3-27b-it","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":25.27,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_vision_creative_writing_elo","value":1166.307155546709,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":1258,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/o4-mini","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":19.91,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_vision_creative_writing_elo","value":1158.7301372277589,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":1531,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.4-nano","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":16.69,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3","source":"arena","metric":"arena_vision_creative_writing_elo","value":1145.8992505914296,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":480,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-medium-3","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":28.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_vision_creative_writing_elo","value":1126.3210298263893,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":238,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-scout","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":41.01,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_vision_creative_writing_elo","value":1123.004410466056,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":771,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"mistralai/mistral-small-3.1-24b-instruct","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":24.46,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_vision_creative_writing_elo","value":1113.3818239508764,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":241,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"z-ai/glm-4.6v","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":40.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_vision_creative_writing_elo","value":1099.0434373975943,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_vision_creative_writing_elo_votes","value":214,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"meta-llama/llama-4-maverick","source":"arena","metric":"arena_vision_creative_writing_elo_interval","value":42.72,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/vision"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_search_elo","value":1261.1307593350664,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/search"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_search_elo_votes","value":60437,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/search"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_search_elo_interval","value":6.29,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/search"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_search_elo","value":1261.0761861904762,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/search"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_search_elo_votes","value":1870,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/search"},{"modelId":"qwen/qwen3.8-max-0902","source":"arena","metric":"arena_search_elo_interval","value":13.18,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/search"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_search_elo","value":1245.8454338407687,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/search"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_search_elo_votes","value":12782,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/search"},{"modelId":"anthropic/claude-fable-5.1","source":"arena","metric":"arena_search_elo_interval","value":7.05,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/search"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_search_elo","value":1241.5675643501204,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/search"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_search_elo_votes","value":13285,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/search"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_search_elo_interval","value":6.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/search"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_search_elo","value":1230.1465939891823,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/search"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_search_elo_votes","value":127506,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/search"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_search_elo_interval","value":4.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/search"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_search_elo","value":1229.1397516536,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/search"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_search_elo_votes","value":73596,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/search"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_search_elo_interval","value":6.51,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/search"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_search_elo","value":1215.9370825422614,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/search"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_search_elo_votes","value":76458,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/search"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_search_elo_interval","value":5.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/search"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_search_elo","value":1212.752524435077,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/search"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_search_elo_votes","value":10842,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/search"},{"modelId":"anthropic/claude-opus-5.5","source":"arena","metric":"arena_search_elo_interval","value":7.09,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/search"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_search_elo","value":1204.1091608362344,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/search"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_search_elo_votes","value":106304,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/search"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_search_elo_interval","value":5.62,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/search"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_search_elo","value":1165.805999435794,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/search"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_search_elo_votes","value":128393,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/search"},{"modelId":"x-ai/grok-4.3","source":"arena","metric":"arena_search_elo_interval","value":4.73,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/search"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_document_elo","value":1516.2663910026604,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_document_elo_votes","value":8794,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"anthropic/claude-opus-5","source":"arena","metric":"arena_document_elo_interval","value":7.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_document_elo","value":1507.3187845894272,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_document_elo_votes","value":27929,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"anthropic/claude-opus-4.6","source":"arena","metric":"arena_document_elo_interval","value":6.42,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_document_elo","value":1496.0822362465265,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_document_elo_votes","value":8497,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"anthropic/claude-fable-5","source":"arena","metric":"arena_document_elo_interval","value":7.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_document_elo","value":1495.0390463625913,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_document_elo_votes","value":22192,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"anthropic/claude-opus-4.7","source":"arena","metric":"arena_document_elo_interval","value":6.37,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_document_elo","value":1485.7193136054452,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_document_elo_votes","value":21279,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"openai/gpt-5.5","source":"arena","metric":"arena_document_elo_interval","value":6.24,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_document_elo","value":1482.7123255544448,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_document_elo_votes","value":4818,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"openai/gpt-5.6-sol","source":"arena","metric":"arena_document_elo_interval","value":8.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_document_elo","value":1482.23522561877,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_document_elo_votes","value":57813,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"anthropic/claude-sonnet-4.6","source":"arena","metric":"arena_document_elo_interval","value":5.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_document_elo","value":1474.788449846873,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_document_elo_votes","value":11551,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"anthropic/claude-opus-4.8","source":"arena","metric":"arena_document_elo_interval","value":6.9,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_document_elo","value":1471.5811447461108,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_document_elo_votes","value":5787,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"openai/gpt-5.6-terra","source":"arena","metric":"arena_document_elo_interval","value":8.27,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_document_elo","value":1471.0043734130195,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_document_elo_votes","value":33331,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"openai/gpt-5.4","source":"arena","metric":"arena_document_elo_interval","value":6.04,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_document_elo","value":1466.136518831971,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_document_elo_votes","value":7411,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"anthropic/claude-sonnet-5","source":"arena","metric":"arena_document_elo_interval","value":7.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_document_elo","value":1464.7005226650015,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_document_elo_votes","value":4885,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"meta/muse-spark-1.1","source":"arena","metric":"arena_document_elo_interval","value":8.84,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_document_elo","value":1463.2738281558122,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_document_elo_votes","value":6500,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"google/gemini-3.5-flash","source":"arena","metric":"arena_document_elo_interval","value":7.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_document_elo","value":1462.1982192559744,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_document_elo_votes","value":7981,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"anthropic/claude-opus-4.5","source":"arena","metric":"arena_document_elo_interval","value":10.41,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_document_elo","value":1456.916653229613,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_document_elo_votes","value":5766,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"openai/gpt-5.6-luna","source":"arena","metric":"arena_document_elo_interval","value":8.2,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_document_elo","value":1456.057486273054,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_document_elo_votes","value":2975,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"google/gemini-3.6-flash","source":"arena","metric":"arena_document_elo_interval","value":10.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_document_elo","value":1452.3297871123095,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_document_elo_votes","value":2258,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"x-ai/grok-4.6","source":"arena","metric":"arena_document_elo_interval","value":12.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_document_elo","value":1451.9590443080492,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_document_elo_votes","value":4965,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"x-ai/grok-4.5","source":"arena","metric":"arena_document_elo_interval","value":8.7,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_document_elo","value":1450.7397099818368,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_document_elo_votes","value":11291,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"moonshotai/kimi-k2.6","source":"arena","metric":"arena_document_elo_interval","value":7.64,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_document_elo","value":1449.8080646641465,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_document_elo_votes","value":31455,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"anthropic/claude-sonnet-4.5","source":"arena","metric":"arena_document_elo_interval","value":6.12,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_document_elo","value":1444.1444013632026,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_document_elo_votes","value":4591,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"qwen/qwen3.7-plus","source":"arena","metric":"arena_document_elo_interval","value":9.02,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_document_elo","value":1443.9187054358893,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_document_elo_votes","value":49457,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"google/gemini-3.1-pro-preview","source":"arena","metric":"arena_document_elo_interval","value":5.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_document_elo","value":1434.7938037275746,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_document_elo_votes","value":6314,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"minimax/minimax-m3","source":"arena","metric":"arena_document_elo_interval","value":8.26,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_document_elo","value":1424.5122273663578,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_document_elo_votes","value":12326,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"google/gemma-4-31b-it","source":"arena","metric":"arena_document_elo_interval","value":7.8,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_document_elo","value":1421.2344901606084,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_document_elo_votes","value":25110,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"google/gemini-2.5-pro","source":"arena","metric":"arena_document_elo_interval","value":6.25,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_document_elo","value":1419.965425258912,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_document_elo_votes","value":34677,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"anthropic/claude-haiku-4.5","source":"arena","metric":"arena_document_elo_interval","value":5.87,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_document_elo","value":1415.5933758703818,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_document_elo_votes","value":6995,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"z-ai/glm-5v-turbo","source":"arena","metric":"arena_document_elo_interval","value":8.22,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_document_elo","value":1404.5908350822938,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_document_elo_votes","value":7108,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"openai/gpt-5.2","source":"arena","metric":"arena_document_elo_interval","value":9.5,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_document_elo","value":1403.1671458960845,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_document_elo_votes","value":8244,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"openai/gpt-5.1","source":"arena","metric":"arena_document_elo_interval","value":9.34,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/document"},{"modelId":"google/gemini-nano-banana-2.1","source":"arena","metric":"arena_text_to_image_elo","value":1327.7839011200813,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text_to_image"},{"modelId":"google/gemini-nano-banana-2.1","source":"arena","metric":"arena_text_to_image_elo_votes","value":5310,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text_to_image"},{"modelId":"google/gemini-nano-banana-2.1","source":"arena","metric":"arena_text_to_image_elo_interval","value":8.76,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text_to_image"},{"modelId":"google/gemini-3.1-flash-lite-image","source":"arena","metric":"arena_text_to_image_elo","value":1250.2355534204482,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text_to_image"},{"modelId":"google/gemini-3.1-flash-lite-image","source":"arena","metric":"arena_text_to_image_elo_votes","value":17804,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text_to_image"},{"modelId":"google/gemini-3.1-flash-lite-image","source":"arena","metric":"arena_text_to_image_elo_interval","value":5.96,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text_to_image"},{"modelId":"google/gemini-3-pro-image-preview","source":"arena","metric":"arena_text_to_image_elo","value":1234.0680818406342,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text_to_image"},{"modelId":"google/gemini-3-pro-image-preview","source":"arena","metric":"arena_text_to_image_elo_votes","value":86464,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text_to_image"},{"modelId":"google/gemini-3-pro-image-preview","source":"arena","metric":"arena_text_to_image_elo_interval","value":4.86,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/text_to_image"},{"modelId":"google/gemini-nano-banana-2.1","source":"arena","metric":"arena_image_edit_elo","value":1428.1107291228673,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/image_edit"},{"modelId":"google/gemini-nano-banana-2.1","source":"arena","metric":"arena_image_edit_elo_votes","value":12985,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/image_edit"},{"modelId":"google/gemini-nano-banana-2.1","source":"arena","metric":"arena_image_edit_elo_interval","value":5.78,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/image_edit"},{"modelId":"google/gemini-3-pro-image-preview","source":"arena","metric":"arena_image_edit_elo","value":1385.9590732069653,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/image_edit"},{"modelId":"google/gemini-3-pro-image-preview","source":"arena","metric":"arena_image_edit_elo_votes","value":540775,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/image_edit"},{"modelId":"google/gemini-3-pro-image-preview","source":"arena","metric":"arena_image_edit_elo_interval","value":2.82,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/image_edit"},{"modelId":"google/gemini-3.1-flash-lite-image","source":"arena","metric":"arena_image_edit_elo","value":1313.513043737679,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/image_edit"},{"modelId":"google/gemini-3.1-flash-lite-image","source":"arena","metric":"arena_image_edit_elo_votes","value":65669,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/image_edit"},{"modelId":"google/gemini-3.1-flash-lite-image","source":"arena","metric":"arena_image_edit_elo_interval","value":4.71,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://lmarena.ai/leaderboard/image_edit"},{"modelId":"meta/muse-wonder","source":"designarena","metric":"design_website_elo","value":1360,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-wonder","source":"designarena","metric":"design_website_elo_battles","value":4167,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.3","source":"designarena","metric":"design_website_elo","value":1356,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.3","source":"designarena","metric":"design_website_elo_battles","value":27827,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-astra","source":"designarena","metric":"design_website_elo","value":1338,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-astra","source":"designarena","metric":"design_website_elo_battles","value":2236,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5.5","source":"designarena","metric":"design_website_elo","value":1336,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5.5","source":"designarena","metric":"design_website_elo_battles","value":2127,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k3","source":"designarena","metric":"design_website_elo","value":1335,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k3","source":"designarena","metric":"design_website_elo_battles","value":4110,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5.5","source":"designarena","metric":"design_website_elo","value":1326,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5.5","source":"designarena","metric":"design_website_elo_battles","value":1834,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-sol","source":"designarena","metric":"design_website_elo","value":1321,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-sol","source":"designarena","metric":"design_website_elo_battles","value":7152,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6.1-sol","source":"designarena","metric":"design_website_elo","value":1320,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6.1-sol","source":"designarena","metric":"design_website_elo_battles","value":2111,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-4-argon","source":"designarena","metric":"design_website_elo","value":1315,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-4-argon","source":"designarena","metric":"design_website_elo_battles","value":7702,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.2","source":"designarena","metric":"design_website_elo","value":1313,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.2","source":"designarena","metric":"design_website_elo_battles","value":31709,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5.1","source":"designarena","metric":"design_website_elo","value":1313,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5.1","source":"designarena","metric":"design_website_elo_battles","value":6043,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"designarena","metric":"design_website_elo","value":1312,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"designarena","metric":"design_website_elo_battles","value":946,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5","source":"designarena","metric":"design_website_elo","value":1310,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5","source":"designarena","metric":"design_website_elo_battles","value":10184,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"designarena","metric":"design_website_elo","value":1309,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"designarena","metric":"design_website_elo_battles","value":26282,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-open","source":"designarena","metric":"design_website_elo","value":1306,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-open","source":"designarena","metric":"design_website_elo_battles","value":230,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.7-flash","source":"designarena","metric":"design_website_elo","value":1304,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.7-flash","source":"designarena","metric":"design_website_elo_battles","value":57032,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.8-flash","source":"designarena","metric":"design_website_elo","value":1301,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.8-flash","source":"designarena","metric":"design_website_elo_battles","value":29381,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.6-flash","source":"designarena","metric":"design_website_elo","value":1300,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.6-flash","source":"designarena","metric":"design_website_elo_battles","value":15658,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5","source":"designarena","metric":"design_website_elo","value":1296,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5","source":"designarena","metric":"design_website_elo_battles","value":10872,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-sol","source":"designarena","metric":"design_website_elo","value":1292,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-sol","source":"designarena","metric":"design_website_elo_battles","value":2685,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.6","source":"designarena","metric":"design_website_elo","value":1291,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.6","source":"designarena","metric":"design_website_elo_battles","value":14720,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.6","source":"designarena","metric":"design_website_elo","value":1285,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.6","source":"designarena","metric":"design_website_elo_battles","value":13777,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.2","source":"designarena","metric":"design_website_elo","value":1285,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.2","source":"designarena","metric":"design_website_elo_battles","value":35577,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.8-max-0902","source":"designarena","metric":"design_website_elo","value":1276,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.8-max-0902","source":"designarena","metric":"design_website_elo_battles","value":6135,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-max","source":"designarena","metric":"design_website_elo","value":1274,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-max","source":"designarena","metric":"design_website_elo_battles","value":18357,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5","source":"designarena","metric":"design_website_elo","value":1274,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5","source":"designarena","metric":"design_website_elo_battles","value":13569,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-luna","source":"designarena","metric":"design_website_elo","value":1271,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-luna","source":"designarena","metric":"design_website_elo_battles","value":3851,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-plus","source":"designarena","metric":"design_website_elo","value":1270,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-plus","source":"designarena","metric":"design_website_elo_battles","value":10167,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.6","source":"designarena","metric":"design_website_elo","value":1269,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.6","source":"designarena","metric":"design_website_elo_battles","value":13690,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-terra","source":"designarena","metric":"design_website_elo","value":1269,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-terra","source":"designarena","metric":"design_website_elo_battles","value":36762,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.5-flash","source":"designarena","metric":"design_website_elo","value":1268,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.5-flash","source":"designarena","metric":"design_website_elo_battles","value":20793,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"designarena","metric":"design_website_elo","value":1267,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"designarena","metric":"design_website_elo_battles","value":15905,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.5","source":"designarena","metric":"design_website_elo","value":1266,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.5","source":"designarena","metric":"design_website_elo_battles","value":24218,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.7-code","source":"designarena","metric":"design_website_elo","value":1264,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.7-code","source":"designarena","metric":"design_website_elo_battles","value":12606,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-haiku-5.5","source":"designarena","metric":"design_website_elo","value":1263,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-haiku-5.5","source":"designarena","metric":"design_website_elo_battles","value":6853,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5-turbo","source":"designarena","metric":"design_website_elo","value":1262,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5-turbo","source":"designarena","metric":"design_website_elo_battles","value":25363,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.8","source":"designarena","metric":"design_website_elo","value":1259,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.8","source":"designarena","metric":"design_website_elo_battles","value":19529,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m3","source":"designarena","metric":"design_website_elo","value":1258,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m3","source":"designarena","metric":"design_website_elo_battles","value":16301,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-large-4-0","source":"designarena","metric":"design_website_elo","value":1258,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-large-4-0","source":"designarena","metric":"design_website_elo_battles","value":3010,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.5","source":"designarena","metric":"design_website_elo","value":1257,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.5","source":"designarena","metric":"design_website_elo_battles","value":18901,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-luna","source":"designarena","metric":"design_website_elo","value":1256,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-luna","source":"designarena","metric":"design_website_elo_battles","value":13154,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.7","source":"designarena","metric":"design_website_elo","value":1253,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.7","source":"designarena","metric":"design_website_elo_battles","value":1532,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.5","source":"designarena","metric":"design_website_elo","value":1249,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.5","source":"designarena","metric":"design_website_elo_battles","value":23394,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5","source":"designarena","metric":"design_website_elo","value":1248,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5","source":"designarena","metric":"design_website_elo_battles","value":24173,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.5","source":"designarena","metric":"design_website_elo","value":1247,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.5","source":"designarena","metric":"design_website_elo_battles","value":21788,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.6-plus","source":"designarena","metric":"design_website_elo","value":1243,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.6-plus","source":"designarena","metric":"design_website_elo_battles","value":16128,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"designarena","metric":"design_website_elo","value":1238,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"designarena","metric":"design_website_elo_battles","value":6610,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-pro","source":"designarena","metric":"design_website_elo","value":1235,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-pro","source":"designarena","metric":"design_website_elo_battles","value":15533,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-pro-preview","source":"designarena","metric":"design_website_elo","value":1234,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-pro-preview","source":"designarena","metric":"design_website_elo_battles","value":28255,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"tencent/hy3","source":"designarena","metric":"design_website_elo","value":1231,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"tencent/hy3","source":"designarena","metric":"design_website_elo_battles","value":19361,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5v-turbo","source":"designarena","metric":"design_website_elo","value":1230,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5v-turbo","source":"designarena","metric":"design_website_elo_battles","value":26493,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7","source":"designarena","metric":"design_website_elo","value":1226,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7","source":"designarena","metric":"design_website_elo_battles","value":30294,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"thinkingmachines/inkling","source":"designarena","metric":"design_website_elo","value":1224,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"thinkingmachines/inkling","source":"designarena","metric":"design_website_elo_battles","value":10867,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-flash","source":"designarena","metric":"design_website_elo","value":1208,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-flash","source":"designarena","metric":"design_website_elo_battles","value":13462,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2.1","source":"designarena","metric":"design_website_elo","value":1202,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2.1","source":"designarena","metric":"design_website_elo_battles","value":15158,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.4","source":"designarena","metric":"design_website_elo","value":1199,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.4","source":"designarena","metric":"design_website_elo_battles","value":13180,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3-flash-preview","source":"designarena","metric":"design_website_elo","value":1196,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3-flash-preview","source":"designarena","metric":"design_website_elo_battles","value":3461,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.3","source":"designarena","metric":"design_website_elo","value":1196,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.3","source":"designarena","metric":"design_website_elo_battles","value":21528,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"stepfun/step-3.7-flash","source":"designarena","metric":"design_website_elo","value":1196,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"stepfun/step-3.7-flash","source":"designarena","metric":"design_website_elo_battles","value":18363,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7-flash","source":"designarena","metric":"design_website_elo","value":1194,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7-flash","source":"designarena","metric":"design_website_elo_battles","value":7792,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"designarena","metric":"design_website_elo","value":1191,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"designarena","metric":"design_website_elo_battles","value":5253,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.5","source":"designarena","metric":"design_website_elo","value":1190,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.5","source":"designarena","metric":"design_website_elo_battles","value":29170,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.5-plus-02-15","source":"designarena","metric":"design_website_elo","value":1188,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.5-plus-02-15","source":"designarena","metric":"design_website_elo_battles","value":11011,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1","source":"designarena","metric":"design_website_elo","value":1187,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1","source":"designarena","metric":"design_website_elo_battles","value":11385,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5","source":"designarena","metric":"design_website_elo","value":1185,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5","source":"designarena","metric":"design_website_elo_battles","value":22203,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"designarena","metric":"design_website_elo","value":1179,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"designarena","metric":"design_website_elo_battles","value":14351,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.1","source":"designarena","metric":"design_website_elo","value":1177,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.1","source":"designarena","metric":"design_website_elo_battles","value":12297,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"upstage/solar-pro4","source":"designarena","metric":"design_website_elo","value":1177,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"upstage/solar-pro4","source":"designarena","metric":"design_website_elo_battles","value":12507,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.2","source":"designarena","metric":"design_website_elo","value":1175,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.2","source":"designarena","metric":"design_website_elo_battles","value":17922,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.6","source":"designarena","metric":"design_website_elo","value":1174,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.6","source":"designarena","metric":"design_website_elo_battles","value":12435,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.5","source":"designarena","metric":"design_website_elo","value":1170,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.5","source":"designarena","metric":"design_website_elo_battles","value":14853,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"designarena","metric":"design_website_elo","value":1169,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"designarena","metric":"design_website_elo_battles","value":1607,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-2.5-pro","source":"designarena","metric":"design_website_elo","value":1167,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-2.5-pro","source":"designarena","metric":"design_website_elo_battles","value":5223,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.3-codex","source":"designarena","metric":"design_website_elo","value":1163,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.3-codex","source":"designarena","metric":"design_website_elo_battles","value":8722,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1-codex","source":"designarena","metric":"design_website_elo","value":1162,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1-codex","source":"designarena","metric":"design_website_elo_battles","value":1453,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-large-2512","source":"designarena","metric":"design_website_elo","value":1162,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-large-2512","source":"designarena","metric":"design_website_elo_battles","value":19081,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"upstage/solar-mini4","source":"designarena","metric":"design_website_elo","value":1161,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"upstage/solar-mini4","source":"designarena","metric":"design_website_elo_battles","value":1354,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-coder","source":"designarena","metric":"design_website_elo","value":1159,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-coder","source":"designarena","metric":"design_website_elo_battles","value":1405,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-r1-0528","source":"designarena","metric":"design_website_elo","value":1149,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-r1-0528","source":"designarena","metric":"design_website_elo_battles","value":13889,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.5-air","source":"designarena","metric":"design_website_elo","value":1147,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.5-air","source":"designarena","metric":"design_website_elo_battles","value":13436,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"designarena","metric":"design_website_elo","value":1145,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"designarena","metric":"design_website_elo_battles","value":14075,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3-5","source":"designarena","metric":"design_website_elo","value":1142,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3-5","source":"designarena","metric":"design_website_elo_battles","value":5825,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"arcee-ai/trinity-large-thinking","source":"designarena","metric":"design_website_elo","value":1137,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"arcee-ai/trinity-large-thinking","source":"designarena","metric":"design_website_elo_battles","value":7091,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3.1","source":"designarena","metric":"design_website_elo","value":1133,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3.1","source":"designarena","metric":"design_website_elo_battles","value":17128,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5-mini","source":"designarena","metric":"design_website_elo","value":1125,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5-mini","source":"designarena","metric":"design_website_elo_battles","value":23958,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-haiku-4.5","source":"designarena","metric":"design_website_elo","value":1122,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-haiku-4.5","source":"designarena","metric":"design_website_elo_battles","value":23935,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-chat","source":"designarena","metric":"design_website_elo","value":1120,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-chat","source":"designarena","metric":"design_website_elo_battles","value":14738,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2-thinking","source":"designarena","metric":"design_website_elo","value":1113,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2-thinking","source":"designarena","metric":"design_website_elo_battles","value":713,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1-codex-mini","source":"designarena","metric":"design_website_elo","value":1111,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1-codex-mini","source":"designarena","metric":"design_website_elo_battles","value":22494,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5-nano","source":"designarena","metric":"design_website_elo","value":1102,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5-nano","source":"designarena","metric":"design_website_elo_battles","value":5413,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2-0905","source":"designarena","metric":"design_website_elo","value":1089,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2-0905","source":"designarena","metric":"design_website_elo_battles","value":235,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-coder-30b-a3b-instruct","source":"designarena","metric":"design_website_elo","value":1088,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-coder-30b-a3b-instruct","source":"designarena","metric":"design_website_elo_battles","value":760,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"designarena","metric":"design_website_elo","value":1083,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"designarena","metric":"design_website_elo_battles","value":13750,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/ministral-14b-2512","source":"designarena","metric":"design_website_elo","value":1081,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/ministral-14b-2512","source":"designarena","metric":"design_website_elo_battles","value":1934,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3","source":"designarena","metric":"design_website_elo","value":1079,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3","source":"designarena","metric":"design_website_elo_battles","value":4766,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-2.5-flash","source":"designarena","metric":"design_website_elo","value":1074,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-2.5-flash","source":"designarena","metric":"design_website_elo_battles","value":5495,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/ministral-8b-2512","source":"designarena","metric":"design_website_elo","value":1065,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/ministral-8b-2512","source":"designarena","metric":"design_website_elo_battles","value":1945,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"designarena","metric":"design_website_elo","value":1058,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"designarena","metric":"design_website_elo_battles","value":5402,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"designarena","metric":"design_website_elo","value":1053,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"designarena","metric":"design_website_elo_battles","value":4938,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2","source":"designarena","metric":"design_website_elo","value":1051,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2","source":"designarena","metric":"design_website_elo_battles","value":897,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4.1","source":"designarena","metric":"design_website_elo","value":1039,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4.1","source":"designarena","metric":"design_website_elo_battles","value":1146,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"inception/mercury-2","source":"designarena","metric":"design_website_elo","value":1036,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"inception/mercury-2","source":"designarena","metric":"design_website_elo_battles","value":14161,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/ministral-3b-2512","source":"designarena","metric":"design_website_elo","value":1028,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/ministral-3b-2512","source":"designarena","metric":"design_website_elo_battles","value":2319,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/codestral-2508","source":"designarena","metric":"design_website_elo","value":1013,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/codestral-2508","source":"designarena","metric":"design_website_elo_battles","value":5344,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4.1-mini","source":"designarena","metric":"design_website_elo","value":998,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4.1-mini","source":"designarena","metric":"design_website_elo_battles","value":956,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4.1-nano","source":"designarena","metric":"design_website_elo","value":973,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4.1-nano","source":"designarena","metric":"design_website_elo_battles","value":1158,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-oss-120b","source":"designarena","metric":"design_website_elo","value":968,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-oss-120b","source":"designarena","metric":"design_website_elo_battles","value":4144,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-30b-a3b","source":"designarena","metric":"design_website_elo","value":955,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-30b-a3b","source":"designarena","metric":"design_website_elo_battles","value":1854,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta-llama/llama-4-maverick","source":"designarena","metric":"design_website_elo","value":871,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta-llama/llama-4-maverick","source":"designarena","metric":"design_website_elo_battles","value":1039,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-oss-20b","source":"designarena","metric":"design_website_elo","value":853,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-oss-20b","source":"designarena","metric":"design_website_elo_battles","value":627,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"amazon/nova-premier-v1","source":"designarena","metric":"design_website_elo","value":835,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"amazon/nova-premier-v1","source":"designarena","metric":"design_website_elo_battles","value":386,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4o","source":"designarena","metric":"design_website_elo","value":831,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4o","source":"designarena","metric":"design_website_elo_battles","value":1062,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"amazon/nova-pro-v1","source":"designarena","metric":"design_website_elo","value":796,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"amazon/nova-pro-v1","source":"designarena","metric":"design_website_elo_battles","value":482,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta-llama/llama-4-scout","source":"designarena","metric":"design_website_elo","value":750,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta-llama/llama-4-scout","source":"designarena","metric":"design_website_elo_battles","value":752,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-astra","source":"designarena","metric":"design_ui_elo","value":1400,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-astra","source":"designarena","metric":"design_ui_elo_battles","value":561,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5.5","source":"designarena","metric":"design_ui_elo","value":1386,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5.5","source":"designarena","metric":"design_ui_elo_battles","value":371,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-wonder","source":"designarena","metric":"design_ui_elo","value":1375,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-wonder","source":"designarena","metric":"design_ui_elo_battles","value":266,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5.5","source":"designarena","metric":"design_ui_elo","value":1372,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5.5","source":"designarena","metric":"design_ui_elo_battles","value":317,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.3","source":"designarena","metric":"design_ui_elo","value":1352,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.3","source":"designarena","metric":"design_ui_elo_battles","value":1346,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5","source":"designarena","metric":"design_ui_elo","value":1348,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5","source":"designarena","metric":"design_ui_elo_battles","value":1605,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k3","source":"designarena","metric":"design_ui_elo","value":1346,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k3","source":"designarena","metric":"design_ui_elo_battles","value":499,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.8-max-0902","source":"designarena","metric":"design_ui_elo","value":1340,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.8-max-0902","source":"designarena","metric":"design_ui_elo_battles","value":977,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5.1","source":"designarena","metric":"design_ui_elo","value":1339,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5.1","source":"designarena","metric":"design_ui_elo_battles","value":684,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-sol","source":"designarena","metric":"design_ui_elo","value":1338,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-sol","source":"designarena","metric":"design_ui_elo_battles","value":807,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-4-argon","source":"designarena","metric":"design_ui_elo","value":1333,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-4-argon","source":"designarena","metric":"design_ui_elo_battles","value":542,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5","source":"designarena","metric":"design_ui_elo","value":1319,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5","source":"designarena","metric":"design_ui_elo_battles","value":1547,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.8-flash","source":"designarena","metric":"design_ui_elo","value":1318,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.8-flash","source":"designarena","metric":"design_ui_elo_battles","value":1754,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6.1-sol","source":"designarena","metric":"design_ui_elo","value":1317,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6.1-sol","source":"designarena","metric":"design_ui_elo_battles","value":184,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"designarena","metric":"design_ui_elo","value":1315,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"designarena","metric":"design_ui_elo_battles","value":1202,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"designarena","metric":"design_ui_elo","value":1306,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"designarena","metric":"design_ui_elo_battles","value":142,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.7-flash","source":"designarena","metric":"design_ui_elo","value":1301,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.7-flash","source":"designarena","metric":"design_ui_elo_battles","value":1904,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.2","source":"designarena","metric":"design_ui_elo","value":1301,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.2","source":"designarena","metric":"design_ui_elo_battles","value":1908,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-luna","source":"designarena","metric":"design_ui_elo","value":1299,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-luna","source":"designarena","metric":"design_ui_elo_battles","value":1425,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.6-flash","source":"designarena","metric":"design_ui_elo","value":1297,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.6-flash","source":"designarena","metric":"design_ui_elo_battles","value":1864,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.2","source":"designarena","metric":"design_ui_elo","value":1296,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.2","source":"designarena","metric":"design_ui_elo_battles","value":1829,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-haiku-5.5","source":"designarena","metric":"design_ui_elo","value":1295,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-haiku-5.5","source":"designarena","metric":"design_ui_elo_battles","value":278,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-sol","source":"designarena","metric":"design_ui_elo","value":1291,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-sol","source":"designarena","metric":"design_ui_elo_battles","value":893,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.6","source":"designarena","metric":"design_ui_elo","value":1285,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.6","source":"designarena","metric":"design_ui_elo_battles","value":2319,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5","source":"designarena","metric":"design_ui_elo","value":1279,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5","source":"designarena","metric":"design_ui_elo_battles","value":2552,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-large-4-0","source":"designarena","metric":"design_ui_elo","value":1275,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-large-4-0","source":"designarena","metric":"design_ui_elo_battles","value":416,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.5-flash","source":"designarena","metric":"design_ui_elo","value":1273,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.5-flash","source":"designarena","metric":"design_ui_elo_battles","value":3192,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.6","source":"designarena","metric":"design_ui_elo","value":1272,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.6","source":"designarena","metric":"design_ui_elo_battles","value":2167,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-max","source":"designarena","metric":"design_ui_elo","value":1270,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-max","source":"designarena","metric":"design_ui_elo_battles","value":2116,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.7","source":"designarena","metric":"design_ui_elo","value":1268,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.7","source":"designarena","metric":"design_ui_elo_battles","value":291,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.6","source":"designarena","metric":"design_ui_elo","value":1267,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.6","source":"designarena","metric":"design_ui_elo_battles","value":3157,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5-turbo","source":"designarena","metric":"design_ui_elo","value":1264,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5-turbo","source":"designarena","metric":"design_ui_elo_battles","value":2917,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-plus","source":"designarena","metric":"design_ui_elo","value":1263,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-plus","source":"designarena","metric":"design_ui_elo_battles","value":1369,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.5","source":"designarena","metric":"design_ui_elo","value":1260,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.5","source":"designarena","metric":"design_ui_elo_battles","value":2526,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.7-code","source":"designarena","metric":"design_ui_elo","value":1260,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.7-code","source":"designarena","metric":"design_ui_elo_battles","value":1927,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-terra","source":"designarena","metric":"design_ui_elo","value":1259,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-terra","source":"designarena","metric":"design_ui_elo_battles","value":6982,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.8","source":"designarena","metric":"design_ui_elo","value":1258,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.8","source":"designarena","metric":"design_ui_elo_battles","value":2340,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.5","source":"designarena","metric":"design_ui_elo","value":1258,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.5","source":"designarena","metric":"design_ui_elo_battles","value":4251,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-luna","source":"designarena","metric":"design_ui_elo","value":1252,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-luna","source":"designarena","metric":"design_ui_elo_battles","value":1809,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"designarena","metric":"design_ui_elo","value":1248,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"designarena","metric":"design_ui_elo_battles","value":1521,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m3","source":"designarena","metric":"design_ui_elo","value":1247,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m3","source":"designarena","metric":"design_ui_elo_battles","value":1841,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.5","source":"designarena","metric":"design_ui_elo","value":1239,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.5","source":"designarena","metric":"design_ui_elo_battles","value":2085,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1-codex","source":"designarena","metric":"design_ui_elo","value":1238,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1-codex","source":"designarena","metric":"design_ui_elo_battles","value":115,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.5","source":"designarena","metric":"design_ui_elo","value":1237,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.5","source":"designarena","metric":"design_ui_elo_battles","value":3531,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"designarena","metric":"design_ui_elo","value":1236,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"designarena","metric":"design_ui_elo_battles","value":496,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.6-plus","source":"designarena","metric":"design_ui_elo","value":1233,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.6-plus","source":"designarena","metric":"design_ui_elo_battles","value":4357,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5","source":"designarena","metric":"design_ui_elo","value":1231,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5","source":"designarena","metric":"design_ui_elo_battles","value":3908,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-pro-preview","source":"designarena","metric":"design_ui_elo","value":1227,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-pro-preview","source":"designarena","metric":"design_ui_elo_battles","value":3328,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2.1","source":"designarena","metric":"design_ui_elo","value":1223,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2.1","source":"designarena","metric":"design_ui_elo_battles","value":746,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-pro","source":"designarena","metric":"design_ui_elo","value":1222,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-pro","source":"designarena","metric":"design_ui_elo_battles","value":2145,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.4","source":"designarena","metric":"design_ui_elo","value":1216,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.4","source":"designarena","metric":"design_ui_elo_battles","value":129,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5v-turbo","source":"designarena","metric":"design_ui_elo","value":1214,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5v-turbo","source":"designarena","metric":"design_ui_elo_battles","value":3212,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7-flash","source":"designarena","metric":"design_ui_elo","value":1208,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7-flash","source":"designarena","metric":"design_ui_elo_battles","value":583,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"tencent/hy3","source":"designarena","metric":"design_ui_elo","value":1206,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"tencent/hy3","source":"designarena","metric":"design_ui_elo_battles","value":1549,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7","source":"designarena","metric":"design_ui_elo","value":1200,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7","source":"designarena","metric":"design_ui_elo_battles","value":2898,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"thinkingmachines/inkling","source":"designarena","metric":"design_ui_elo","value":1200,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"thinkingmachines/inkling","source":"designarena","metric":"design_ui_elo_battles","value":1407,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.3","source":"designarena","metric":"design_ui_elo","value":1193,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.3","source":"designarena","metric":"design_ui_elo_battles","value":3955,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"stepfun/step-3.7-flash","source":"designarena","metric":"design_ui_elo","value":1181,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"stepfun/step-3.7-flash","source":"designarena","metric":"design_ui_elo_battles","value":2150,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5","source":"designarena","metric":"design_ui_elo","value":1180,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5","source":"designarena","metric":"design_ui_elo_battles","value":458,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.5-plus-02-15","source":"designarena","metric":"design_ui_elo","value":1178,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.5-plus-02-15","source":"designarena","metric":"design_ui_elo_battles","value":1238,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.5","source":"designarena","metric":"design_ui_elo","value":1173,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.5","source":"designarena","metric":"design_ui_elo_battles","value":2412,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"designarena","metric":"design_ui_elo","value":1167,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"designarena","metric":"design_ui_elo_battles","value":752,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1","source":"designarena","metric":"design_ui_elo","value":1167,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1","source":"designarena","metric":"design_ui_elo_battles","value":854,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.1","source":"designarena","metric":"design_ui_elo","value":1165,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.1","source":"designarena","metric":"design_ui_elo_battles","value":431,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-flash","source":"designarena","metric":"design_ui_elo","value":1165,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-flash","source":"designarena","metric":"design_ui_elo_battles","value":1577,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"designarena","metric":"design_ui_elo","value":1164,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"designarena","metric":"design_ui_elo_battles","value":488,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"upstage/solar-pro4","source":"designarena","metric":"design_ui_elo","value":1150,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"upstage/solar-pro4","source":"designarena","metric":"design_ui_elo_battles","value":1049,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.2","source":"designarena","metric":"design_ui_elo","value":1149,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.2","source":"designarena","metric":"design_ui_elo_battles","value":1615,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.6","source":"designarena","metric":"design_ui_elo","value":1148,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.6","source":"designarena","metric":"design_ui_elo_battles","value":686,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.5","source":"designarena","metric":"design_ui_elo","value":1144,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.5","source":"designarena","metric":"design_ui_elo_battles","value":607,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"designarena","metric":"design_ui_elo","value":1140,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"designarena","metric":"design_ui_elo_battles","value":1512,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-2.5-pro","source":"designarena","metric":"design_ui_elo","value":1140,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-2.5-pro","source":"designarena","metric":"design_ui_elo_battles","value":572,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.3-codex","source":"designarena","metric":"design_ui_elo","value":1138,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.3-codex","source":"designarena","metric":"design_ui_elo_battles","value":1051,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"designarena","metric":"design_ui_elo","value":1128,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"designarena","metric":"design_ui_elo_battles","value":111,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.5-air","source":"designarena","metric":"design_ui_elo","value":1124,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.5-air","source":"designarena","metric":"design_ui_elo_battles","value":465,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-coder","source":"designarena","metric":"design_ui_elo","value":1113,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-coder","source":"designarena","metric":"design_ui_elo_battles","value":207,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5-mini","source":"designarena","metric":"design_ui_elo","value":1106,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5-mini","source":"designarena","metric":"design_ui_elo_battles","value":2100,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-r1-0528","source":"designarena","metric":"design_ui_elo","value":1103,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-r1-0528","source":"designarena","metric":"design_ui_elo_battles","value":530,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-large-2512","source":"designarena","metric":"design_ui_elo","value":1102,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-large-2512","source":"designarena","metric":"design_ui_elo_battles","value":1735,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-haiku-4.5","source":"designarena","metric":"design_ui_elo","value":1100,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-haiku-4.5","source":"designarena","metric":"design_ui_elo_battles","value":1865,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3.1","source":"designarena","metric":"design_ui_elo","value":1100,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3.1","source":"designarena","metric":"design_ui_elo_battles","value":1708,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-chat","source":"designarena","metric":"design_ui_elo","value":1094,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-chat","source":"designarena","metric":"design_ui_elo_battles","value":581,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1-codex-mini","source":"designarena","metric":"design_ui_elo","value":1081,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1-codex-mini","source":"designarena","metric":"design_ui_elo_battles","value":1837,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3-5","source":"designarena","metric":"design_ui_elo","value":1079,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3-5","source":"designarena","metric":"design_ui_elo_battles","value":889,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"designarena","metric":"design_ui_elo","value":1072,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"designarena","metric":"design_ui_elo_battles","value":1521,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5-nano","source":"designarena","metric":"design_ui_elo","value":1067,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5-nano","source":"designarena","metric":"design_ui_elo_battles","value":268,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-coder-30b-a3b-instruct","source":"designarena","metric":"design_ui_elo","value":1047,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-coder-30b-a3b-instruct","source":"designarena","metric":"design_ui_elo_battles","value":122,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"arcee-ai/trinity-large-thinking","source":"designarena","metric":"design_ui_elo","value":1045,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"arcee-ai/trinity-large-thinking","source":"designarena","metric":"design_ui_elo_battles","value":841,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2","source":"designarena","metric":"design_ui_elo","value":1031,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2","source":"designarena","metric":"design_ui_elo_battles","value":138,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3","source":"designarena","metric":"design_ui_elo","value":1025,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3","source":"designarena","metric":"design_ui_elo_battles","value":365,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/codestral-2508","source":"designarena","metric":"design_ui_elo","value":1017,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/codestral-2508","source":"designarena","metric":"design_ui_elo_battles","value":257,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-2.5-flash","source":"designarena","metric":"design_ui_elo","value":1006,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-2.5-flash","source":"designarena","metric":"design_ui_elo_battles","value":298,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4.1","source":"designarena","metric":"design_ui_elo","value":1001,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4.1","source":"designarena","metric":"design_ui_elo_battles","value":155,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"inception/mercury-2","source":"designarena","metric":"design_ui_elo","value":998,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"inception/mercury-2","source":"designarena","metric":"design_ui_elo_battles","value":1535,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"designarena","metric":"design_ui_elo","value":966,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"designarena","metric":"design_ui_elo_battles","value":380,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4.1-mini","source":"designarena","metric":"design_ui_elo","value":961,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4.1-mini","source":"designarena","metric":"design_ui_elo_battles","value":172,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-30b-a3b","source":"designarena","metric":"design_ui_elo","value":946,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-30b-a3b","source":"designarena","metric":"design_ui_elo_battles","value":264,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"designarena","metric":"design_ui_elo","value":945,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"designarena","metric":"design_ui_elo_battles","value":244,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-oss-120b","source":"designarena","metric":"design_ui_elo","value":927,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-oss-120b","source":"designarena","metric":"design_ui_elo_battles","value":269,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4.1-nano","source":"designarena","metric":"design_ui_elo","value":916,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4.1-nano","source":"designarena","metric":"design_ui_elo_battles","value":173,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta-llama/llama-4-maverick","source":"designarena","metric":"design_ui_elo","value":900,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta-llama/llama-4-maverick","source":"designarena","metric":"design_ui_elo_battles","value":184,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4o","source":"designarena","metric":"design_ui_elo","value":886,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4o","source":"designarena","metric":"design_ui_elo_battles","value":197,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta-llama/llama-4-scout","source":"designarena","metric":"design_ui_elo","value":768,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta-llama/llama-4-scout","source":"designarena","metric":"design_ui_elo_battles","value":157,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-astra","source":"designarena","metric":"design_gamedev_elo","value":1474,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-astra","source":"designarena","metric":"design_gamedev_elo_battles","value":631,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5.5","source":"designarena","metric":"design_gamedev_elo","value":1472,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5.5","source":"designarena","metric":"design_gamedev_elo_battles","value":519,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5.5","source":"designarena","metric":"design_gamedev_elo","value":1458,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5.5","source":"designarena","metric":"design_gamedev_elo_battles","value":765,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6.1-sol","source":"designarena","metric":"design_gamedev_elo","value":1390,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6.1-sol","source":"designarena","metric":"design_gamedev_elo_battles","value":687,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5.1","source":"designarena","metric":"design_gamedev_elo","value":1381,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5.1","source":"designarena","metric":"design_gamedev_elo_battles","value":1497,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-wonder","source":"designarena","metric":"design_gamedev_elo","value":1378,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-wonder","source":"designarena","metric":"design_gamedev_elo_battles","value":748,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"designarena","metric":"design_gamedev_elo","value":1373,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"designarena","metric":"design_gamedev_elo_battles","value":631,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-4-argon","source":"designarena","metric":"design_gamedev_elo","value":1372,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-4-argon","source":"designarena","metric":"design_gamedev_elo_battles","value":1209,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-sol","source":"designarena","metric":"design_gamedev_elo","value":1369,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-sol","source":"designarena","metric":"design_gamedev_elo_battles","value":2201,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k3","source":"designarena","metric":"design_gamedev_elo","value":1362,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k3","source":"designarena","metric":"design_gamedev_elo_battles","value":827,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5","source":"designarena","metric":"design_gamedev_elo","value":1337,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5","source":"designarena","metric":"design_gamedev_elo_battles","value":3013,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5","source":"designarena","metric":"design_gamedev_elo","value":1335,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5","source":"designarena","metric":"design_gamedev_elo_battles","value":3461,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"designarena","metric":"design_gamedev_elo","value":1331,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"designarena","metric":"design_gamedev_elo_battles","value":12254,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.3","source":"designarena","metric":"design_gamedev_elo","value":1329,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.3","source":"designarena","metric":"design_gamedev_elo_battles","value":12050,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.7-flash","source":"designarena","metric":"design_gamedev_elo","value":1318,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.7-flash","source":"designarena","metric":"design_gamedev_elo_battles","value":14101,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-haiku-5.5","source":"designarena","metric":"design_gamedev_elo","value":1316,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-haiku-5.5","source":"designarena","metric":"design_gamedev_elo_battles","value":1562,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.8-max-0902","source":"designarena","metric":"design_gamedev_elo","value":1313,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.8-max-0902","source":"designarena","metric":"design_gamedev_elo_battles","value":2640,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.7","source":"designarena","metric":"design_gamedev_elo","value":1313,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.7","source":"designarena","metric":"design_gamedev_elo_battles","value":687,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-sol","source":"designarena","metric":"design_gamedev_elo","value":1310,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-sol","source":"designarena","metric":"design_gamedev_elo_battles","value":1310,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.8-flash","source":"designarena","metric":"design_gamedev_elo","value":1305,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.8-flash","source":"designarena","metric":"design_gamedev_elo_battles","value":12491,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.2","source":"designarena","metric":"design_gamedev_elo","value":1302,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.2","source":"designarena","metric":"design_gamedev_elo_battles","value":12826,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.5","source":"designarena","metric":"design_gamedev_elo","value":1294,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.5","source":"designarena","metric":"design_gamedev_elo_battles","value":7164,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-open","source":"designarena","metric":"design_gamedev_elo","value":1283,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-open","source":"designarena","metric":"design_gamedev_elo_battles","value":170,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5","source":"designarena","metric":"design_gamedev_elo","value":1279,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5","source":"designarena","metric":"design_gamedev_elo_battles","value":3429,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.6","source":"designarena","metric":"design_gamedev_elo","value":1277,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.6","source":"designarena","metric":"design_gamedev_elo_battles","value":2745,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.2","source":"designarena","metric":"design_gamedev_elo","value":1269,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.2","source":"designarena","metric":"design_gamedev_elo_battles","value":7825,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-max","source":"designarena","metric":"design_gamedev_elo","value":1265,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-max","source":"designarena","metric":"design_gamedev_elo_battles","value":6513,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.8","source":"designarena","metric":"design_gamedev_elo","value":1263,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.8","source":"designarena","metric":"design_gamedev_elo_battles","value":4894,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.5-flash","source":"designarena","metric":"design_gamedev_elo","value":1263,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.5-flash","source":"designarena","metric":"design_gamedev_elo_battles","value":6101,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.6-flash","source":"designarena","metric":"design_gamedev_elo","value":1263,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.6-flash","source":"designarena","metric":"design_gamedev_elo_battles","value":5608,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-plus","source":"designarena","metric":"design_gamedev_elo","value":1262,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-plus","source":"designarena","metric":"design_gamedev_elo_battles","value":3640,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"designarena","metric":"design_gamedev_elo","value":1261,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"designarena","metric":"design_gamedev_elo_battles","value":4792,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.6","source":"designarena","metric":"design_gamedev_elo","value":1259,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.6","source":"designarena","metric":"design_gamedev_elo_battles","value":4485,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-luna","source":"designarena","metric":"design_gamedev_elo","value":1259,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-luna","source":"designarena","metric":"design_gamedev_elo_battles","value":1352,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.6","source":"designarena","metric":"design_gamedev_elo","value":1250,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.6","source":"designarena","metric":"design_gamedev_elo_battles","value":5031,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5-turbo","source":"designarena","metric":"design_gamedev_elo","value":1249,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5-turbo","source":"designarena","metric":"design_gamedev_elo_battles","value":5385,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.5","source":"designarena","metric":"design_gamedev_elo","value":1249,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.5","source":"designarena","metric":"design_gamedev_elo_battles","value":5705,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5","source":"designarena","metric":"design_gamedev_elo","value":1234,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5","source":"designarena","metric":"design_gamedev_elo_battles","value":5689,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-terra","source":"designarena","metric":"design_gamedev_elo","value":1230,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-terra","source":"designarena","metric":"design_gamedev_elo_battles","value":14796,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.5","source":"designarena","metric":"design_gamedev_elo","value":1229,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.5","source":"designarena","metric":"design_gamedev_elo_battles","value":5034,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-pro","source":"designarena","metric":"design_gamedev_elo","value":1229,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-pro","source":"designarena","metric":"design_gamedev_elo_battles","value":4413,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-large-4-0","source":"designarena","metric":"design_gamedev_elo","value":1226,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-large-4-0","source":"designarena","metric":"design_gamedev_elo_battles","value":1406,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.7-code","source":"designarena","metric":"design_gamedev_elo","value":1220,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.7-code","source":"designarena","metric":"design_gamedev_elo_battles","value":3703,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5v-turbo","source":"designarena","metric":"design_gamedev_elo","value":1218,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5v-turbo","source":"designarena","metric":"design_gamedev_elo_battles","value":7864,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.6-plus","source":"designarena","metric":"design_gamedev_elo","value":1211,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.6-plus","source":"designarena","metric":"design_gamedev_elo_battles","value":8168,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m3","source":"designarena","metric":"design_gamedev_elo","value":1210,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m3","source":"designarena","metric":"design_gamedev_elo_battles","value":4423,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"tencent/hy3","source":"designarena","metric":"design_gamedev_elo","value":1209,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"tencent/hy3","source":"designarena","metric":"design_gamedev_elo_battles","value":3074,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"designarena","metric":"design_gamedev_elo","value":1208,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"designarena","metric":"design_gamedev_elo_battles","value":1761,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.5","source":"designarena","metric":"design_gamedev_elo","value":1207,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.5","source":"designarena","metric":"design_gamedev_elo_battles","value":5004,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-pro-preview","source":"designarena","metric":"design_gamedev_elo","value":1202,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-pro-preview","source":"designarena","metric":"design_gamedev_elo_battles","value":7074,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-flash","source":"designarena","metric":"design_gamedev_elo","value":1197,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-flash","source":"designarena","metric":"design_gamedev_elo_battles","value":4371,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.4","source":"designarena","metric":"design_gamedev_elo","value":1195,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.4","source":"designarena","metric":"design_gamedev_elo_battles","value":4000,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-luna","source":"designarena","metric":"design_gamedev_elo","value":1194,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-luna","source":"designarena","metric":"design_gamedev_elo_battles","value":3856,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7","source":"designarena","metric":"design_gamedev_elo","value":1188,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7","source":"designarena","metric":"design_gamedev_elo_battles","value":5108,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5","source":"designarena","metric":"design_gamedev_elo","value":1185,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5","source":"designarena","metric":"design_gamedev_elo_battles","value":1283,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1","source":"designarena","metric":"design_gamedev_elo","value":1179,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1","source":"designarena","metric":"design_gamedev_elo_battles","value":1812,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.3","source":"designarena","metric":"design_gamedev_elo","value":1174,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.3","source":"designarena","metric":"design_gamedev_elo_battles","value":7327,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"inception/mercury-3","source":"designarena","metric":"design_gamedev_elo","value":1172,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"inception/mercury-3","source":"designarena","metric":"design_gamedev_elo_battles","value":121,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.1","source":"designarena","metric":"design_gamedev_elo","value":1171,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.1","source":"designarena","metric":"design_gamedev_elo_battles","value":1524,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"upstage/solar-pro4","source":"designarena","metric":"design_gamedev_elo","value":1170,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"upstage/solar-pro4","source":"designarena","metric":"design_gamedev_elo_battles","value":1025,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.5","source":"designarena","metric":"design_gamedev_elo","value":1166,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.5","source":"designarena","metric":"design_gamedev_elo_battles","value":6024,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3-flash-preview","source":"designarena","metric":"design_gamedev_elo","value":1166,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3-flash-preview","source":"designarena","metric":"design_gamedev_elo_battles","value":369,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"thinkingmachines/inkling","source":"designarena","metric":"design_gamedev_elo","value":1166,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"thinkingmachines/inkling","source":"designarena","metric":"design_gamedev_elo_battles","value":3548,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.3-codex","source":"designarena","metric":"design_gamedev_elo","value":1161,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.3-codex","source":"designarena","metric":"design_gamedev_elo_battles","value":2963,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"stepfun/step-3.7-flash","source":"designarena","metric":"design_gamedev_elo","value":1159,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"stepfun/step-3.7-flash","source":"designarena","metric":"design_gamedev_elo_battles","value":4484,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.6","source":"designarena","metric":"design_gamedev_elo","value":1151,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.6","source":"designarena","metric":"design_gamedev_elo_battles","value":1929,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.5","source":"designarena","metric":"design_gamedev_elo","value":1145,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.5","source":"designarena","metric":"design_gamedev_elo_battles","value":1996,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"designarena","metric":"design_gamedev_elo","value":1144,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"designarena","metric":"design_gamedev_elo_battles","value":2056,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"designarena","metric":"design_gamedev_elo","value":1140,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"designarena","metric":"design_gamedev_elo_battles","value":1162,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1-codex","source":"designarena","metric":"design_gamedev_elo","value":1138,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1-codex","source":"designarena","metric":"design_gamedev_elo_battles","value":182,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"designarena","metric":"design_gamedev_elo","value":1138,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"designarena","metric":"design_gamedev_elo_battles","value":4967,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7-flash","source":"designarena","metric":"design_gamedev_elo","value":1135,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7-flash","source":"designarena","metric":"design_gamedev_elo_battles","value":1560,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2.1","source":"designarena","metric":"design_gamedev_elo","value":1134,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2.1","source":"designarena","metric":"design_gamedev_elo_battles","value":2300,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.2","source":"designarena","metric":"design_gamedev_elo","value":1132,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.2","source":"designarena","metric":"design_gamedev_elo_battles","value":4509,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5-mini","source":"designarena","metric":"design_gamedev_elo","value":1129,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5-mini","source":"designarena","metric":"design_gamedev_elo_battles","value":5244,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"upstage/solar-mini4","source":"designarena","metric":"design_gamedev_elo","value":1121,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"upstage/solar-mini4","source":"designarena","metric":"design_gamedev_elo_battles","value":416,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-2.5-pro","source":"designarena","metric":"design_gamedev_elo","value":1111,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-2.5-pro","source":"designarena","metric":"design_gamedev_elo_battles","value":633,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"designarena","metric":"design_gamedev_elo","value":1109,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"designarena","metric":"design_gamedev_elo_battles","value":927,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.5-plus-02-15","source":"designarena","metric":"design_gamedev_elo","value":1105,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.5-plus-02-15","source":"designarena","metric":"design_gamedev_elo_battles","value":2804,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-coder","source":"designarena","metric":"design_gamedev_elo","value":1099,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-coder","source":"designarena","metric":"design_gamedev_elo_battles","value":155,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-haiku-4.5","source":"designarena","metric":"design_gamedev_elo","value":1097,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-haiku-4.5","source":"designarena","metric":"design_gamedev_elo_battles","value":4502,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-r1-0528","source":"designarena","metric":"design_gamedev_elo","value":1097,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-r1-0528","source":"designarena","metric":"design_gamedev_elo_battles","value":1636,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.5-air","source":"designarena","metric":"design_gamedev_elo","value":1094,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.5-air","source":"designarena","metric":"design_gamedev_elo_battles","value":1660,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1-codex-mini","source":"designarena","metric":"design_gamedev_elo","value":1092,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1-codex-mini","source":"designarena","metric":"design_gamedev_elo_battles","value":4185,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-large-2512","source":"designarena","metric":"design_gamedev_elo","value":1080,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-large-2512","source":"designarena","metric":"design_gamedev_elo_battles","value":4125,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4.1","source":"designarena","metric":"design_gamedev_elo","value":1080,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4.1","source":"designarena","metric":"design_gamedev_elo_battles","value":181,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3-5","source":"designarena","metric":"design_gamedev_elo","value":1079,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3-5","source":"designarena","metric":"design_gamedev_elo_battles","value":1521,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"arcee-ai/trinity-large-thinking","source":"designarena","metric":"design_gamedev_elo","value":1079,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"arcee-ai/trinity-large-thinking","source":"designarena","metric":"design_gamedev_elo_battles","value":2073,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3.1","source":"designarena","metric":"design_gamedev_elo","value":1074,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3.1","source":"designarena","metric":"design_gamedev_elo_battles","value":3816,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4.1-mini","source":"designarena","metric":"design_gamedev_elo","value":1071,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4.1-mini","source":"designarena","metric":"design_gamedev_elo_battles","value":224,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-chat","source":"designarena","metric":"design_gamedev_elo","value":1053,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-chat","source":"designarena","metric":"design_gamedev_elo_battles","value":1891,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5-nano","source":"designarena","metric":"design_gamedev_elo","value":1045,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5-nano","source":"designarena","metric":"design_gamedev_elo_battles","value":533,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/ministral-14b-2512","source":"designarena","metric":"design_gamedev_elo","value":1038,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/ministral-14b-2512","source":"designarena","metric":"design_gamedev_elo_battles","value":149,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"designarena","metric":"design_gamedev_elo","value":1029,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"designarena","metric":"design_gamedev_elo_battles","value":3706,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3","source":"designarena","metric":"design_gamedev_elo","value":1018,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3","source":"designarena","metric":"design_gamedev_elo_battles","value":599,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-2.5-flash","source":"designarena","metric":"design_gamedev_elo","value":1005,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-2.5-flash","source":"designarena","metric":"design_gamedev_elo_battles","value":514,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-oss-120b","source":"designarena","metric":"design_gamedev_elo","value":992,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-oss-120b","source":"designarena","metric":"design_gamedev_elo_battles","value":445,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/ministral-8b-2512","source":"designarena","metric":"design_gamedev_elo","value":990,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/ministral-8b-2512","source":"designarena","metric":"design_gamedev_elo_battles","value":168,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"inception/mercury-2","source":"designarena","metric":"design_gamedev_elo","value":986,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"inception/mercury-2","source":"designarena","metric":"design_gamedev_elo_battles","value":4624,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2","source":"designarena","metric":"design_gamedev_elo","value":974,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2","source":"designarena","metric":"design_gamedev_elo_battles","value":138,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4.1-nano","source":"designarena","metric":"design_gamedev_elo","value":970,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4.1-nano","source":"designarena","metric":"design_gamedev_elo_battles","value":250,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/codestral-2508","source":"designarena","metric":"design_gamedev_elo","value":968,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/codestral-2508","source":"designarena","metric":"design_gamedev_elo_battles","value":576,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"designarena","metric":"design_gamedev_elo","value":957,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"designarena","metric":"design_gamedev_elo_battles","value":514,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"designarena","metric":"design_gamedev_elo","value":952,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"designarena","metric":"design_gamedev_elo_battles","value":558,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/ministral-3b-2512","source":"designarena","metric":"design_gamedev_elo","value":949,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/ministral-3b-2512","source":"designarena","metric":"design_gamedev_elo_battles","value":230,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4o","source":"designarena","metric":"design_gamedev_elo","value":906,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4o","source":"designarena","metric":"design_gamedev_elo_battles","value":241,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-30b-a3b","source":"designarena","metric":"design_gamedev_elo","value":899,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-30b-a3b","source":"designarena","metric":"design_gamedev_elo_battles","value":224,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta-llama/llama-4-maverick","source":"designarena","metric":"design_gamedev_elo","value":838,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta-llama/llama-4-maverick","source":"designarena","metric":"design_gamedev_elo_battles","value":205,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta-llama/llama-4-scout","source":"designarena","metric":"design_gamedev_elo","value":773,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta-llama/llama-4-scout","source":"designarena","metric":"design_gamedev_elo_battles","value":175,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5.5","source":"designarena","metric":"design_dataviz_elo","value":1397,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5.5","source":"designarena","metric":"design_dataviz_elo_battles","value":638,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5.5","source":"designarena","metric":"design_dataviz_elo","value":1387,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5.5","source":"designarena","metric":"design_dataviz_elo_battles","value":109,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k3","source":"designarena","metric":"design_dataviz_elo","value":1350,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k3","source":"designarena","metric":"design_dataviz_elo_battles","value":714,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5.1","source":"designarena","metric":"design_dataviz_elo","value":1344,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5.1","source":"designarena","metric":"design_dataviz_elo_battles","value":437,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.3","source":"designarena","metric":"design_dataviz_elo","value":1343,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.3","source":"designarena","metric":"design_dataviz_elo_battles","value":1363,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-4-argon","source":"designarena","metric":"design_dataviz_elo","value":1336,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-4-argon","source":"designarena","metric":"design_dataviz_elo_battles","value":287,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.2","source":"designarena","metric":"design_dataviz_elo","value":1334,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.2","source":"designarena","metric":"design_dataviz_elo_battles","value":1722,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-astra","source":"designarena","metric":"design_dataviz_elo","value":1333,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-astra","source":"designarena","metric":"design_dataviz_elo_battles","value":356,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5","source":"designarena","metric":"design_dataviz_elo","value":1329,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5","source":"designarena","metric":"design_dataviz_elo_battles","value":1769,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-sol","source":"designarena","metric":"design_dataviz_elo","value":1323,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-sol","source":"designarena","metric":"design_dataviz_elo_battles","value":1450,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.7-flash","source":"designarena","metric":"design_dataviz_elo","value":1315,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.7-flash","source":"designarena","metric":"design_dataviz_elo_battles","value":1703,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5","source":"designarena","metric":"design_dataviz_elo","value":1304,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5","source":"designarena","metric":"design_dataviz_elo_battles","value":1364,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"designarena","metric":"design_dataviz_elo","value":1291,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"designarena","metric":"design_dataviz_elo_battles","value":985,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-haiku-5.5","source":"designarena","metric":"design_dataviz_elo","value":1291,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-haiku-5.5","source":"designarena","metric":"design_dataviz_elo_battles","value":224,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.6-flash","source":"designarena","metric":"design_dataviz_elo","value":1289,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.6-flash","source":"designarena","metric":"design_dataviz_elo_battles","value":3642,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.2","source":"designarena","metric":"design_dataviz_elo","value":1285,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.2","source":"designarena","metric":"design_dataviz_elo_battles","value":3750,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.8-max-0902","source":"designarena","metric":"design_dataviz_elo","value":1281,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.8-max-0902","source":"designarena","metric":"design_dataviz_elo_battles","value":833,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.6","source":"designarena","metric":"design_dataviz_elo","value":1279,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.6","source":"designarena","metric":"design_dataviz_elo_battles","value":1919,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.6","source":"designarena","metric":"design_dataviz_elo","value":1278,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.6","source":"designarena","metric":"design_dataviz_elo_battles","value":1902,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-plus","source":"designarena","metric":"design_dataviz_elo","value":1276,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-plus","source":"designarena","metric":"design_dataviz_elo_battles","value":1409,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-max","source":"designarena","metric":"design_dataviz_elo","value":1276,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-max","source":"designarena","metric":"design_dataviz_elo_battles","value":2510,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-large-4-0","source":"designarena","metric":"design_dataviz_elo","value":1274,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-large-4-0","source":"designarena","metric":"design_dataviz_elo_battles","value":404,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.8-flash","source":"designarena","metric":"design_dataviz_elo","value":1271,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.8-flash","source":"designarena","metric":"design_dataviz_elo_battles","value":513,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-sol","source":"designarena","metric":"design_dataviz_elo","value":1271,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-sol","source":"designarena","metric":"design_dataviz_elo_battles","value":394,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.5","source":"designarena","metric":"design_dataviz_elo","value":1265,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.5","source":"designarena","metric":"design_dataviz_elo_battles","value":1640,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5-turbo","source":"designarena","metric":"design_dataviz_elo","value":1264,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5-turbo","source":"designarena","metric":"design_dataviz_elo_battles","value":2686,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"designarena","metric":"design_dataviz_elo","value":1257,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"designarena","metric":"design_dataviz_elo_battles","value":2139,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5","source":"designarena","metric":"design_dataviz_elo","value":1252,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5","source":"designarena","metric":"design_dataviz_elo_battles","value":1549,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.6","source":"designarena","metric":"design_dataviz_elo","value":1249,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.6","source":"designarena","metric":"design_dataviz_elo_battles","value":3369,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.5","source":"designarena","metric":"design_dataviz_elo","value":1249,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.5","source":"designarena","metric":"design_dataviz_elo_battles","value":3038,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.5","source":"designarena","metric":"design_dataviz_elo","value":1243,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.5","source":"designarena","metric":"design_dataviz_elo_battles","value":1495,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-terra","source":"designarena","metric":"design_dataviz_elo","value":1240,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-terra","source":"designarena","metric":"design_dataviz_elo_battles","value":5037,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.8","source":"designarena","metric":"design_dataviz_elo","value":1239,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.8","source":"designarena","metric":"design_dataviz_elo_battles","value":1843,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.5-flash","source":"designarena","metric":"design_dataviz_elo","value":1236,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.5-flash","source":"designarena","metric":"design_dataviz_elo_battles","value":2023,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m3","source":"designarena","metric":"design_dataviz_elo","value":1235,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m3","source":"designarena","metric":"design_dataviz_elo_battles","value":1387,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5","source":"designarena","metric":"design_dataviz_elo","value":1228,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5","source":"designarena","metric":"design_dataviz_elo_battles","value":2803,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.6-plus","source":"designarena","metric":"design_dataviz_elo","value":1228,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.6-plus","source":"designarena","metric":"design_dataviz_elo_battles","value":3504,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.7-code","source":"designarena","metric":"design_dataviz_elo","value":1226,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.7-code","source":"designarena","metric":"design_dataviz_elo_battles","value":1065,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.7","source":"designarena","metric":"design_dataviz_elo","value":1226,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.7","source":"designarena","metric":"design_dataviz_elo_battles","value":135,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-2.5-pro","source":"designarena","metric":"design_dataviz_elo","value":1222,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-2.5-pro","source":"designarena","metric":"design_dataviz_elo_battles","value":148,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5","source":"designarena","metric":"design_dataviz_elo","value":1221,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5","source":"designarena","metric":"design_dataviz_elo_battles","value":233,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.5","source":"designarena","metric":"design_dataviz_elo","value":1219,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.5","source":"designarena","metric":"design_dataviz_elo_battles","value":2906,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-luna","source":"designarena","metric":"design_dataviz_elo","value":1213,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-luna","source":"designarena","metric":"design_dataviz_elo_battles","value":493,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1-codex","source":"designarena","metric":"design_dataviz_elo","value":1213,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1-codex","source":"designarena","metric":"design_dataviz_elo_battles","value":118,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-luna","source":"designarena","metric":"design_dataviz_elo","value":1210,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-luna","source":"designarena","metric":"design_dataviz_elo_battles","value":1032,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-pro-preview","source":"designarena","metric":"design_dataviz_elo","value":1209,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-pro-preview","source":"designarena","metric":"design_dataviz_elo_battles","value":2418,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2.1","source":"designarena","metric":"design_dataviz_elo","value":1206,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2.1","source":"designarena","metric":"design_dataviz_elo_battles","value":442,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1","source":"designarena","metric":"design_dataviz_elo","value":1204,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1","source":"designarena","metric":"design_dataviz_elo_battles","value":464,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-pro","source":"designarena","metric":"design_dataviz_elo","value":1203,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-pro","source":"designarena","metric":"design_dataviz_elo_battles","value":1172,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5v-turbo","source":"designarena","metric":"design_dataviz_elo","value":1202,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5v-turbo","source":"designarena","metric":"design_dataviz_elo_battles","value":2854,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.4","source":"designarena","metric":"design_dataviz_elo","value":1196,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.4","source":"designarena","metric":"design_dataviz_elo_battles","value":1191,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7","source":"designarena","metric":"design_dataviz_elo","value":1195,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7","source":"designarena","metric":"design_dataviz_elo_battles","value":1710,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.5-air","source":"designarena","metric":"design_dataviz_elo","value":1186,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.5-air","source":"designarena","metric":"design_dataviz_elo_battles","value":217,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-r1-0528","source":"designarena","metric":"design_dataviz_elo","value":1182,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-r1-0528","source":"designarena","metric":"design_dataviz_elo_battles","value":266,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"designarena","metric":"design_dataviz_elo","value":1180,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"designarena","metric":"design_dataviz_elo_battles","value":401,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.3","source":"designarena","metric":"design_dataviz_elo","value":1179,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.3","source":"designarena","metric":"design_dataviz_elo_battles","value":3200,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"upstage/solar-pro4","source":"designarena","metric":"design_dataviz_elo","value":1177,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"upstage/solar-pro4","source":"designarena","metric":"design_dataviz_elo_battles","value":603,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"designarena","metric":"design_dataviz_elo","value":1175,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"designarena","metric":"design_dataviz_elo_battles","value":267,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"stepfun/step-3.7-flash","source":"designarena","metric":"design_dataviz_elo","value":1172,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"stepfun/step-3.7-flash","source":"designarena","metric":"design_dataviz_elo_battles","value":1706,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.5","source":"designarena","metric":"design_dataviz_elo","value":1167,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.5","source":"designarena","metric":"design_dataviz_elo_battles","value":1820,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.1","source":"designarena","metric":"design_dataviz_elo","value":1166,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.1","source":"designarena","metric":"design_dataviz_elo_battles","value":172,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.3-codex","source":"designarena","metric":"design_dataviz_elo","value":1164,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.3-codex","source":"designarena","metric":"design_dataviz_elo_battles","value":720,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"tencent/hy3","source":"designarena","metric":"design_dataviz_elo","value":1163,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"tencent/hy3","source":"designarena","metric":"design_dataviz_elo_battles","value":1209,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.6","source":"designarena","metric":"design_dataviz_elo","value":1161,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.6","source":"designarena","metric":"design_dataviz_elo_battles","value":365,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"thinkingmachines/inkling","source":"designarena","metric":"design_dataviz_elo","value":1161,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"thinkingmachines/inkling","source":"designarena","metric":"design_dataviz_elo_battles","value":659,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.5","source":"designarena","metric":"design_dataviz_elo","value":1159,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.5","source":"designarena","metric":"design_dataviz_elo_battles","value":319,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.2","source":"designarena","metric":"design_dataviz_elo","value":1158,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.2","source":"designarena","metric":"design_dataviz_elo_battles","value":1102,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"designarena","metric":"design_dataviz_elo","value":1152,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"designarena","metric":"design_dataviz_elo_battles","value":352,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3.1","source":"designarena","metric":"design_dataviz_elo","value":1144,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3.1","source":"designarena","metric":"design_dataviz_elo_battles","value":1131,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"designarena","metric":"design_dataviz_elo","value":1141,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"designarena","metric":"design_dataviz_elo_battles","value":1175,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-large-2512","source":"designarena","metric":"design_dataviz_elo","value":1136,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-large-2512","source":"designarena","metric":"design_dataviz_elo_battles","value":1091,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.5-plus-02-15","source":"designarena","metric":"design_dataviz_elo","value":1135,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.5-plus-02-15","source":"designarena","metric":"design_dataviz_elo_battles","value":920,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5-mini","source":"designarena","metric":"design_dataviz_elo","value":1131,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5-mini","source":"designarena","metric":"design_dataviz_elo_battles","value":1333,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-flash","source":"designarena","metric":"design_dataviz_elo","value":1127,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-flash","source":"designarena","metric":"design_dataviz_elo_battles","value":1106,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-haiku-4.5","source":"designarena","metric":"design_dataviz_elo","value":1124,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-haiku-4.5","source":"designarena","metric":"design_dataviz_elo_battles","value":1131,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7-flash","source":"designarena","metric":"design_dataviz_elo","value":1123,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7-flash","source":"designarena","metric":"design_dataviz_elo_battles","value":311,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3-5","source":"designarena","metric":"design_dataviz_elo","value":1120,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3-5","source":"designarena","metric":"design_dataviz_elo_battles","value":811,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"arcee-ai/trinity-large-thinking","source":"designarena","metric":"design_dataviz_elo","value":1098,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"arcee-ai/trinity-large-thinking","source":"designarena","metric":"design_dataviz_elo_battles","value":718,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1-codex-mini","source":"designarena","metric":"design_dataviz_elo","value":1097,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1-codex-mini","source":"designarena","metric":"design_dataviz_elo_battles","value":1216,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-chat","source":"designarena","metric":"design_dataviz_elo","value":1089,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-chat","source":"designarena","metric":"design_dataviz_elo_battles","value":240,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"designarena","metric":"design_dataviz_elo","value":1070,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"designarena","metric":"design_dataviz_elo_battles","value":147,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-2.5-flash","source":"designarena","metric":"design_dataviz_elo","value":1060,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-2.5-flash","source":"designarena","metric":"design_dataviz_elo_battles","value":169,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5-nano","source":"designarena","metric":"design_dataviz_elo","value":1056,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5-nano","source":"designarena","metric":"design_dataviz_elo_battles","value":106,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"designarena","metric":"design_dataviz_elo","value":1045,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"designarena","metric":"design_dataviz_elo_battles","value":1164,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3","source":"designarena","metric":"design_dataviz_elo","value":1034,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3","source":"designarena","metric":"design_dataviz_elo_battles","value":148,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/codestral-2508","source":"designarena","metric":"design_dataviz_elo","value":1017,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/codestral-2508","source":"designarena","metric":"design_dataviz_elo_battles","value":112,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"inception/mercury-2","source":"designarena","metric":"design_dataviz_elo","value":1010,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"inception/mercury-2","source":"designarena","metric":"design_dataviz_elo_battles","value":1086,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-oss-120b","source":"designarena","metric":"design_dataviz_elo","value":987,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-oss-120b","source":"designarena","metric":"design_dataviz_elo_battles","value":101,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4.1-nano","source":"designarena","metric":"design_dataviz_elo","value":891,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4.1-nano","source":"designarena","metric":"design_dataviz_elo_battles","value":107,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-astra","source":"designarena","metric":"design_3d_elo","value":1505,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-astra","source":"designarena","metric":"design_3d_elo_battles","value":251,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5.5","source":"designarena","metric":"design_3d_elo","value":1477,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5.5","source":"designarena","metric":"design_3d_elo_battles","value":857,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6.1-sol","source":"designarena","metric":"design_3d_elo","value":1461,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6.1-sol","source":"designarena","metric":"design_3d_elo_battles","value":357,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5.5","source":"designarena","metric":"design_3d_elo","value":1458,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5.5","source":"designarena","metric":"design_3d_elo_battles","value":255,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-wonder","source":"designarena","metric":"design_3d_elo","value":1427,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-wonder","source":"designarena","metric":"design_3d_elo_battles","value":601,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5.1","source":"designarena","metric":"design_3d_elo","value":1393,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5.1","source":"designarena","metric":"design_3d_elo_battles","value":1271,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-4-argon","source":"designarena","metric":"design_3d_elo","value":1389,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-4-argon","source":"designarena","metric":"design_3d_elo_battles","value":1071,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k3","source":"designarena","metric":"design_3d_elo","value":1388,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k3","source":"designarena","metric":"design_3d_elo_battles","value":3366,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-sol","source":"designarena","metric":"design_3d_elo","value":1385,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-sol","source":"designarena","metric":"design_3d_elo_battles","value":2446,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.3","source":"designarena","metric":"design_3d_elo","value":1359,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.3","source":"designarena","metric":"design_3d_elo_battles","value":5490,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"designarena","metric":"design_3d_elo","value":1356,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"designarena","metric":"design_3d_elo_battles","value":5313,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"designarena","metric":"design_3d_elo","value":1355,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"designarena","metric":"design_3d_elo_battles","value":150,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-haiku-5.5","source":"designarena","metric":"design_3d_elo","value":1344,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-haiku-5.5","source":"designarena","metric":"design_3d_elo_battles","value":758,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.8-max-0902","source":"designarena","metric":"design_3d_elo","value":1337,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.8-max-0902","source":"designarena","metric":"design_3d_elo_battles","value":3285,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5","source":"designarena","metric":"design_3d_elo","value":1335,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5","source":"designarena","metric":"design_3d_elo_battles","value":3719,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-sol","source":"designarena","metric":"design_3d_elo","value":1321,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-sol","source":"designarena","metric":"design_3d_elo_battles","value":483,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5","source":"designarena","metric":"design_3d_elo","value":1319,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5","source":"designarena","metric":"design_3d_elo_battles","value":4617,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.7-flash","source":"designarena","metric":"design_3d_elo","value":1307,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.7-flash","source":"designarena","metric":"design_3d_elo_battles","value":7625,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.2","source":"designarena","metric":"design_3d_elo","value":1301,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.2","source":"designarena","metric":"design_3d_elo_battles","value":6586,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.8-flash","source":"designarena","metric":"design_3d_elo","value":1295,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.8-flash","source":"designarena","metric":"design_3d_elo_battles","value":6286,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.2","source":"designarena","metric":"design_3d_elo","value":1288,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.2","source":"designarena","metric":"design_3d_elo_battles","value":7898,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.6","source":"designarena","metric":"design_3d_elo","value":1274,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.6","source":"designarena","metric":"design_3d_elo_battles","value":5862,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.6-flash","source":"designarena","metric":"design_3d_elo","value":1272,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.6-flash","source":"designarena","metric":"design_3d_elo_battles","value":7916,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.6","source":"designarena","metric":"design_3d_elo","value":1268,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.6","source":"designarena","metric":"design_3d_elo_battles","value":13980,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.7","source":"designarena","metric":"design_3d_elo","value":1267,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.7","source":"designarena","metric":"design_3d_elo_battles","value":320,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-max","source":"designarena","metric":"design_3d_elo","value":1266,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-max","source":"designarena","metric":"design_3d_elo_battles","value":6886,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5","source":"designarena","metric":"design_3d_elo","value":1261,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5","source":"designarena","metric":"design_3d_elo_battles","value":5326,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-pro","source":"designarena","metric":"design_3d_elo","value":1254,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-pro","source":"designarena","metric":"design_3d_elo_battles","value":4513,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-large-4-0","source":"designarena","metric":"design_3d_elo","value":1253,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-large-4-0","source":"designarena","metric":"design_3d_elo_battles","value":1341,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5-turbo","source":"designarena","metric":"design_3d_elo","value":1248,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5-turbo","source":"designarena","metric":"design_3d_elo_battles","value":5641,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.5-flash","source":"designarena","metric":"design_3d_elo","value":1244,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.5-flash","source":"designarena","metric":"design_3d_elo_battles","value":7356,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"designarena","metric":"design_3d_elo","value":1244,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"designarena","metric":"design_3d_elo_battles","value":4248,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.7-code","source":"designarena","metric":"design_3d_elo","value":1241,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.7-code","source":"designarena","metric":"design_3d_elo_battles","value":6660,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-plus","source":"designarena","metric":"design_3d_elo","value":1239,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-plus","source":"designarena","metric":"design_3d_elo_battles","value":5098,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.6","source":"designarena","metric":"design_3d_elo","value":1234,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.6","source":"designarena","metric":"design_3d_elo_battles","value":5715,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-pro-preview","source":"designarena","metric":"design_3d_elo","value":1234,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-pro-preview","source":"designarena","metric":"design_3d_elo_battles","value":9108,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"tencent/hy3","source":"designarena","metric":"design_3d_elo","value":1233,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"tencent/hy3","source":"designarena","metric":"design_3d_elo_battles","value":4167,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5","source":"designarena","metric":"design_3d_elo","value":1229,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5","source":"designarena","metric":"design_3d_elo_battles","value":9258,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.8","source":"designarena","metric":"design_3d_elo","value":1223,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.8","source":"designarena","metric":"design_3d_elo_battles","value":7335,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.5","source":"designarena","metric":"design_3d_elo","value":1216,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.5","source":"designarena","metric":"design_3d_elo_battles","value":11011,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-luna","source":"designarena","metric":"design_3d_elo","value":1216,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-luna","source":"designarena","metric":"design_3d_elo_battles","value":701,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.5","source":"designarena","metric":"design_3d_elo","value":1214,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.5","source":"designarena","metric":"design_3d_elo_battles","value":6015,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5v-turbo","source":"designarena","metric":"design_3d_elo","value":1209,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5v-turbo","source":"designarena","metric":"design_3d_elo_battles","value":13379,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m3","source":"designarena","metric":"design_3d_elo","value":1209,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m3","source":"designarena","metric":"design_3d_elo_battles","value":4883,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"designarena","metric":"design_3d_elo","value":1209,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"designarena","metric":"design_3d_elo_battles","value":1232,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.5","source":"designarena","metric":"design_3d_elo","value":1205,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.5","source":"designarena","metric":"design_3d_elo_battles","value":11631,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.6-plus","source":"designarena","metric":"design_3d_elo","value":1202,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.6-plus","source":"designarena","metric":"design_3d_elo_battles","value":12691,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.5","source":"designarena","metric":"design_3d_elo","value":1198,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.5","source":"designarena","metric":"design_3d_elo_battles","value":5740,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7","source":"designarena","metric":"design_3d_elo","value":1191,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7","source":"designarena","metric":"design_3d_elo_battles","value":7009,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-flash","source":"designarena","metric":"design_3d_elo","value":1189,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-flash","source":"designarena","metric":"design_3d_elo_battles","value":8028,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3-flash-preview","source":"designarena","metric":"design_3d_elo","value":1184,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3-flash-preview","source":"designarena","metric":"design_3d_elo_battles","value":467,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"upstage/solar-pro4","source":"designarena","metric":"design_3d_elo","value":1178,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"upstage/solar-pro4","source":"designarena","metric":"design_3d_elo_battles","value":2694,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.5","source":"designarena","metric":"design_3d_elo","value":1170,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.5","source":"designarena","metric":"design_3d_elo_battles","value":1878,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2.1","source":"designarena","metric":"design_3d_elo","value":1165,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2.1","source":"designarena","metric":"design_3d_elo_battles","value":2159,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"designarena","metric":"design_3d_elo","value":1161,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"designarena","metric":"design_3d_elo_battles","value":960,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"thinkingmachines/inkling","source":"designarena","metric":"design_3d_elo","value":1161,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"thinkingmachines/inkling","source":"designarena","metric":"design_3d_elo_battles","value":2334,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.5","source":"designarena","metric":"design_3d_elo","value":1158,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.5","source":"designarena","metric":"design_3d_elo_battles","value":7374,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.1","source":"designarena","metric":"design_3d_elo","value":1153,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.1","source":"designarena","metric":"design_3d_elo_battles","value":5947,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"designarena","metric":"design_3d_elo","value":1148,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"designarena","metric":"design_3d_elo_battles","value":1976,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-terra","source":"designarena","metric":"design_3d_elo","value":1135,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-terra","source":"designarena","metric":"design_3d_elo_battles","value":17440,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.2","source":"designarena","metric":"design_3d_elo","value":1133,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.2","source":"designarena","metric":"design_3d_elo_battles","value":4161,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"designarena","metric":"design_3d_elo","value":1132,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"designarena","metric":"design_3d_elo_battles","value":4096,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"designarena","metric":"design_3d_elo","value":1132,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"designarena","metric":"design_3d_elo_battles","value":192,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.6","source":"designarena","metric":"design_3d_elo","value":1129,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.6","source":"designarena","metric":"design_3d_elo_battles","value":1671,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"stepfun/step-3.7-flash","source":"designarena","metric":"design_3d_elo","value":1129,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"stepfun/step-3.7-flash","source":"designarena","metric":"design_3d_elo_battles","value":6897,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.3","source":"designarena","metric":"design_3d_elo","value":1125,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.3","source":"designarena","metric":"design_3d_elo_battles","value":11695,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.5-air","source":"designarena","metric":"design_3d_elo","value":1123,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.5-air","source":"designarena","metric":"design_3d_elo_battles","value":1475,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7-flash","source":"designarena","metric":"design_3d_elo","value":1121,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7-flash","source":"designarena","metric":"design_3d_elo_battles","value":1460,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-luna","source":"designarena","metric":"design_3d_elo","value":1121,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-luna","source":"designarena","metric":"design_3d_elo_battles","value":3772,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.5-plus-02-15","source":"designarena","metric":"design_3d_elo","value":1119,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.5-plus-02-15","source":"designarena","metric":"design_3d_elo_battles","value":2650,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-r1-0528","source":"designarena","metric":"design_3d_elo","value":1111,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-r1-0528","source":"designarena","metric":"design_3d_elo_battles","value":1630,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-large-2512","source":"designarena","metric":"design_3d_elo","value":1099,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-large-2512","source":"designarena","metric":"design_3d_elo_battles","value":4549,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-chat","source":"designarena","metric":"design_3d_elo","value":1087,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-chat","source":"designarena","metric":"design_3d_elo_battles","value":1821,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3","source":"designarena","metric":"design_3d_elo","value":1084,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3","source":"designarena","metric":"design_3d_elo_battles","value":512,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"arcee-ai/trinity-large-thinking","source":"designarena","metric":"design_3d_elo","value":1082,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"arcee-ai/trinity-large-thinking","source":"designarena","metric":"design_3d_elo_battles","value":2117,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-2.5-pro","source":"designarena","metric":"design_3d_elo","value":1081,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-2.5-pro","source":"designarena","metric":"design_3d_elo_battles","value":644,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3.1","source":"designarena","metric":"design_3d_elo","value":1081,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3.1","source":"designarena","metric":"design_3d_elo_battles","value":4180,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-haiku-4.5","source":"designarena","metric":"design_3d_elo","value":1072,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-haiku-4.5","source":"designarena","metric":"design_3d_elo_battles","value":6343,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.4","source":"designarena","metric":"design_3d_elo","value":1065,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.4","source":"designarena","metric":"design_3d_elo_battles","value":4300,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1","source":"designarena","metric":"design_3d_elo","value":1061,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1","source":"designarena","metric":"design_3d_elo_battles","value":1850,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3-5","source":"designarena","metric":"design_3d_elo","value":1061,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3-5","source":"designarena","metric":"design_3d_elo_battles","value":2065,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5","source":"designarena","metric":"design_3d_elo","value":1056,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5","source":"designarena","metric":"design_3d_elo_battles","value":3973,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"designarena","metric":"design_3d_elo","value":1048,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"designarena","metric":"design_3d_elo_battles","value":3836,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5-mini","source":"designarena","metric":"design_3d_elo","value":1037,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5-mini","source":"designarena","metric":"design_3d_elo_battles","value":5580,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/ministral-8b-2512","source":"designarena","metric":"design_3d_elo","value":1032,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/ministral-8b-2512","source":"designarena","metric":"design_3d_elo_battles","value":238,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-2.5-flash","source":"designarena","metric":"design_3d_elo","value":1021,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-2.5-flash","source":"designarena","metric":"design_3d_elo_battles","value":495,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/codestral-2508","source":"designarena","metric":"design_3d_elo","value":1020,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/codestral-2508","source":"designarena","metric":"design_3d_elo_battles","value":445,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.3-codex","source":"designarena","metric":"design_3d_elo","value":1008,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.3-codex","source":"designarena","metric":"design_3d_elo_battles","value":2219,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"designarena","metric":"design_3d_elo","value":998,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"designarena","metric":"design_3d_elo_battles","value":384,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"designarena","metric":"design_3d_elo","value":994,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"designarena","metric":"design_3d_elo_battles","value":452,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/ministral-14b-2512","source":"designarena","metric":"design_3d_elo","value":990,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/ministral-14b-2512","source":"designarena","metric":"design_3d_elo_battles","value":212,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1-codex-mini","source":"designarena","metric":"design_3d_elo","value":988,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1-codex-mini","source":"designarena","metric":"design_3d_elo_battles","value":4527,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"inception/mercury-2","source":"designarena","metric":"design_3d_elo","value":982,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"inception/mercury-2","source":"designarena","metric":"design_3d_elo_battles","value":3782,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5-nano","source":"designarena","metric":"design_3d_elo","value":966,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5-nano","source":"designarena","metric":"design_3d_elo_battles","value":383,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/ministral-3b-2512","source":"designarena","metric":"design_3d_elo","value":963,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/ministral-3b-2512","source":"designarena","metric":"design_3d_elo_battles","value":195,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4.1-nano","source":"designarena","metric":"design_3d_elo","value":925,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4.1-nano","source":"designarena","metric":"design_3d_elo_battles","value":213,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-oss-120b","source":"designarena","metric":"design_3d_elo","value":901,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-oss-120b","source":"designarena","metric":"design_3d_elo_battles","value":313,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta-llama/llama-4-maverick","source":"designarena","metric":"design_3d_elo","value":901,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta-llama/llama-4-maverick","source":"designarena","metric":"design_3d_elo_battles","value":164,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4o","source":"designarena","metric":"design_3d_elo","value":869,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4o","source":"designarena","metric":"design_3d_elo_battles","value":194,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4.1","source":"designarena","metric":"design_3d_elo","value":850,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4.1","source":"designarena","metric":"design_3d_elo_battles","value":181,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4.1-mini","source":"designarena","metric":"design_3d_elo","value":837,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4.1-mini","source":"designarena","metric":"design_3d_elo_battles","value":151,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5.5","source":"designarena","metric":"design_code_overall_elo","value":1390,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5.5","source":"designarena","metric":"design_code_overall_elo_battles","value":4531,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-astra","source":"designarena","metric":"design_code_overall_elo","value":1379,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-astra","source":"designarena","metric":"design_code_overall_elo_battles","value":8813,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-wonder","source":"designarena","metric":"design_code_overall_elo","value":1369,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-wonder","source":"designarena","metric":"design_code_overall_elo_battles","value":5564,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5.5","source":"designarena","metric":"design_code_overall_elo","value":1365,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5.5","source":"designarena","metric":"design_code_overall_elo_battles","value":2850,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k3","source":"designarena","metric":"design_code_overall_elo","value":1361,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k3","source":"designarena","metric":"design_code_overall_elo_battles","value":8934,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.3","source":"designarena","metric":"design_code_overall_elo","value":1353,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.3","source":"designarena","metric":"design_code_overall_elo_battles","value":44398,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6.1-sol","source":"designarena","metric":"design_code_overall_elo","value":1346,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6.1-sol","source":"designarena","metric":"design_code_overall_elo_battles","value":3176,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-sol","source":"designarena","metric":"design_code_overall_elo","value":1342,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-sol","source":"designarena","metric":"design_code_overall_elo_battles","value":13407,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5.1","source":"designarena","metric":"design_code_overall_elo","value":1336,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5.1","source":"designarena","metric":"design_code_overall_elo_battles","value":9349,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"designarena","metric":"design_code_overall_elo","value":1332,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4.1-flash-1017","source":"designarena","metric":"design_code_overall_elo_battles","value":1865,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-4-argon","source":"designarena","metric":"design_code_overall_elo","value":1328,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-4-argon","source":"designarena","metric":"design_code_overall_elo_battles","value":10285,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5","source":"designarena","metric":"design_code_overall_elo","value":1324,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5","source":"designarena","metric":"design_code_overall_elo_battles","value":19145,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"designarena","metric":"design_code_overall_elo","value":1321,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"designarena","metric":"design_code_overall_elo_battles","value":42160,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.2","source":"designarena","metric":"design_code_overall_elo","value":1313,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.2","source":"designarena","metric":"design_code_overall_elo_battles","value":50265,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5","source":"designarena","metric":"design_code_overall_elo","value":1311,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5","source":"designarena","metric":"design_code_overall_elo_battles","value":20216,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.7-flash","source":"designarena","metric":"design_code_overall_elo","value":1309,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.7-flash","source":"designarena","metric":"design_code_overall_elo_battles","value":77346,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.8-flash","source":"designarena","metric":"design_code_overall_elo","value":1304,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.8-flash","source":"designarena","metric":"design_code_overall_elo_battles","value":45871,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-sol","source":"designarena","metric":"design_code_overall_elo","value":1300,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-sol","source":"designarena","metric":"design_code_overall_elo_battles","value":5367,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.8-max-0902","source":"designarena","metric":"design_code_overall_elo","value":1293,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.8-max-0902","source":"designarena","metric":"design_code_overall_elo_battles","value":11172,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.6-flash","source":"designarena","metric":"design_code_overall_elo","value":1290,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.6-flash","source":"designarena","metric":"design_code_overall_elo_battles","value":32546,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.6","source":"designarena","metric":"design_code_overall_elo","value":1289,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.6","source":"designarena","metric":"design_code_overall_elo_battles","value":27406,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.2","source":"designarena","metric":"design_code_overall_elo","value":1288,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.2","source":"designarena","metric":"design_code_overall_elo_battles","value":56742,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-haiku-5.5","source":"designarena","metric":"design_code_overall_elo","value":1279,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-haiku-5.5","source":"designarena","metric":"design_code_overall_elo_battles","value":9118,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.6","source":"designarena","metric":"design_code_overall_elo","value":1276,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.6","source":"designarena","metric":"design_code_overall_elo_battles","value":26317,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5","source":"designarena","metric":"design_code_overall_elo","value":1276,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5","source":"designarena","metric":"design_code_overall_elo_battles","value":24122,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-max","source":"designarena","metric":"design_code_overall_elo","value":1275,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-max","source":"designarena","metric":"design_code_overall_elo_battles","value":36382,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.6","source":"designarena","metric":"design_code_overall_elo","value":1272,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.6","source":"designarena","metric":"design_code_overall_elo_battles","value":34045,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-luna","source":"designarena","metric":"design_code_overall_elo","value":1271,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-luna","source":"designarena","metric":"design_code_overall_elo_battles","value":7051,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.7","source":"designarena","metric":"design_code_overall_elo","value":1270,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.7","source":"designarena","metric":"design_code_overall_elo_battles","value":2792,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-plus","source":"designarena","metric":"design_code_overall_elo","value":1269,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-plus","source":"designarena","metric":"design_code_overall_elo_battles","value":18609,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.5-flash","source":"designarena","metric":"design_code_overall_elo","value":1266,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.5-flash","source":"designarena","metric":"design_code_overall_elo_battles","value":36840,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"designarena","metric":"design_code_overall_elo","value":1266,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"designarena","metric":"design_code_overall_elo_battles","value":28605,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5-turbo","source":"designarena","metric":"design_code_overall_elo","value":1262,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5-turbo","source":"designarena","metric":"design_code_overall_elo_battles","value":41992,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.5","source":"designarena","metric":"design_code_overall_elo","value":1260,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.5","source":"designarena","metric":"design_code_overall_elo_battles","value":33768,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.5","source":"designarena","metric":"design_code_overall_elo","value":1260,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.5","source":"designarena","metric":"design_code_overall_elo_battles","value":44701,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-large-4-0","source":"designarena","metric":"design_code_overall_elo","value":1259,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-large-4-0","source":"designarena","metric":"design_code_overall_elo_battles","value":5988,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.8","source":"designarena","metric":"design_code_overall_elo","value":1255,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.8","source":"designarena","metric":"design_code_overall_elo_battles","value":32708,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.7-code","source":"designarena","metric":"design_code_overall_elo","value":1253,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.7-code","source":"designarena","metric":"design_code_overall_elo_battles","value":22468,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5","source":"designarena","metric":"design_code_overall_elo","value":1247,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5","source":"designarena","metric":"design_code_overall_elo_battles","value":45368,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m3","source":"designarena","metric":"design_code_overall_elo","value":1247,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m3","source":"designarena","metric":"design_code_overall_elo_battles","value":27491,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.5","source":"designarena","metric":"design_code_overall_elo","value":1242,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.5","source":"designarena","metric":"design_code_overall_elo_battles","value":35207,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-terra","source":"designarena","metric":"design_code_overall_elo","value":1242,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-terra","source":"designarena","metric":"design_code_overall_elo_battles","value":74620,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-pro","source":"designarena","metric":"design_code_overall_elo","value":1241,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-pro","source":"designarena","metric":"design_code_overall_elo_battles","value":27276,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.5","source":"designarena","metric":"design_code_overall_elo","value":1237,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.5","source":"designarena","metric":"design_code_overall_elo_battles","value":41642,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.6-plus","source":"designarena","metric":"design_code_overall_elo","value":1236,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.6-plus","source":"designarena","metric":"design_code_overall_elo_battles","value":39105,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-pro-preview","source":"designarena","metric":"design_code_overall_elo","value":1231,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-pro-preview","source":"designarena","metric":"design_code_overall_elo_battles","value":47245,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-luna","source":"designarena","metric":"design_code_overall_elo","value":1231,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-luna","source":"designarena","metric":"design_code_overall_elo_battles","value":21673,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"designarena","metric":"design_code_overall_elo","value":1230,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"designarena","metric":"design_code_overall_elo_battles","value":10439,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5v-turbo","source":"designarena","metric":"design_code_overall_elo","value":1229,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5v-turbo","source":"designarena","metric":"design_code_overall_elo_battles","value":47102,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"tencent/hy3","source":"designarena","metric":"design_code_overall_elo","value":1228,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"tencent/hy3","source":"designarena","metric":"design_code_overall_elo_battles","value":29261,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7","source":"designarena","metric":"design_code_overall_elo","value":1217,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7","source":"designarena","metric":"design_code_overall_elo_battles","value":46849,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-flash","source":"designarena","metric":"design_code_overall_elo","value":1206,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-flash","source":"designarena","metric":"design_code_overall_elo_battles","value":28103,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"thinkingmachines/inkling","source":"designarena","metric":"design_code_overall_elo","value":1206,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"thinkingmachines/inkling","source":"designarena","metric":"design_code_overall_elo_battles","value":18742,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2.1","source":"designarena","metric":"design_code_overall_elo","value":1191,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2.1","source":"designarena","metric":"design_code_overall_elo_battles","value":20805,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3-flash-preview","source":"designarena","metric":"design_code_overall_elo","value":1190,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3-flash-preview","source":"designarena","metric":"design_code_overall_elo_battles","value":4414,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.3","source":"designarena","metric":"design_code_overall_elo","value":1187,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.3","source":"designarena","metric":"design_code_overall_elo_battles","value":41076,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.5","source":"designarena","metric":"design_code_overall_elo","value":1183,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.5","source":"designarena","metric":"design_code_overall_elo_battles","value":45448,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"upstage/solar-pro4","source":"designarena","metric":"design_code_overall_elo","value":1183,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"upstage/solar-pro4","source":"designarena","metric":"design_code_overall_elo_battles","value":17878,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"stepfun/step-3.7-flash","source":"designarena","metric":"design_code_overall_elo","value":1182,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"stepfun/step-3.7-flash","source":"designarena","metric":"design_code_overall_elo_battles","value":29891,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.4","source":"designarena","metric":"design_code_overall_elo","value":1180,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.4","source":"designarena","metric":"design_code_overall_elo_battles","value":21152,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"designarena","metric":"design_code_overall_elo","value":1180,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"designarena","metric":"design_code_overall_elo_battles","value":8130,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7-flash","source":"designarena","metric":"design_code_overall_elo","value":1178,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7-flash","source":"designarena","metric":"design_code_overall_elo_battles","value":11706,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.1","source":"designarena","metric":"design_code_overall_elo","value":1171,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.1","source":"designarena","metric":"design_code_overall_elo_battles","value":15715,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"designarena","metric":"design_code_overall_elo","value":1171,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"designarena","metric":"design_code_overall_elo_battles","value":19487,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1","source":"designarena","metric":"design_code_overall_elo","value":1171,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1","source":"designarena","metric":"design_code_overall_elo_battles","value":16116,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5","source":"designarena","metric":"design_code_overall_elo","value":1168,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5","source":"designarena","metric":"design_code_overall_elo_battles","value":13485,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.5-plus-02-15","source":"designarena","metric":"design_code_overall_elo","value":1167,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.5-plus-02-15","source":"designarena","metric":"design_code_overall_elo_battles","value":18504,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.6","source":"designarena","metric":"design_code_overall_elo","value":1166,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.6","source":"designarena","metric":"design_code_overall_elo_battles","value":17086,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.5","source":"designarena","metric":"design_code_overall_elo","value":1165,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.5","source":"designarena","metric":"design_code_overall_elo_battles","value":19653,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.2","source":"designarena","metric":"design_code_overall_elo","value":1164,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.2","source":"designarena","metric":"design_code_overall_elo_battles","value":29125,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"upstage/solar-mini4","source":"designarena","metric":"design_code_overall_elo","value":1155,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"upstage/solar-mini4","source":"designarena","metric":"design_code_overall_elo_battles","value":2053,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-2.5-pro","source":"designarena","metric":"design_code_overall_elo","value":1153,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-2.5-pro","source":"designarena","metric":"design_code_overall_elo_battles","value":7220,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1-codex","source":"designarena","metric":"design_code_overall_elo","value":1153,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1-codex","source":"designarena","metric":"design_code_overall_elo_battles","value":2005,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"designarena","metric":"design_code_overall_elo","value":1153,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"nvidia/nemotron-3.5-super-vl","source":"designarena","metric":"design_code_overall_elo_battles","value":2728,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"designarena","metric":"design_code_overall_elo","value":1147,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"designarena","metric":"design_code_overall_elo_battles","value":25824,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.3-codex","source":"designarena","metric":"design_code_overall_elo","value":1145,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.3-codex","source":"designarena","metric":"design_code_overall_elo_battles","value":15675,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-coder","source":"designarena","metric":"design_code_overall_elo","value":1143,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-coder","source":"designarena","metric":"design_code_overall_elo_battles","value":1955,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-large-2512","source":"designarena","metric":"design_code_overall_elo","value":1142,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-large-2512","source":"designarena","metric":"design_code_overall_elo_battles","value":30430,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-r1-0528","source":"designarena","metric":"design_code_overall_elo","value":1139,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-r1-0528","source":"designarena","metric":"design_code_overall_elo_battles","value":17951,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.5-air","source":"designarena","metric":"design_code_overall_elo","value":1138,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.5-air","source":"designarena","metric":"design_code_overall_elo_battles","value":17253,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3-5","source":"designarena","metric":"design_code_overall_elo","value":1122,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3-5","source":"designarena","metric":"design_code_overall_elo_battles","value":10894,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3.1","source":"designarena","metric":"design_code_overall_elo","value":1121,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3.1","source":"designarena","metric":"design_code_overall_elo_battles","value":27828,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"arcee-ai/trinity-large-thinking","source":"designarena","metric":"design_code_overall_elo","value":1117,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"arcee-ai/trinity-large-thinking","source":"designarena","metric":"design_code_overall_elo_battles","value":12840,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-haiku-4.5","source":"designarena","metric":"design_code_overall_elo","value":1115,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-haiku-4.5","source":"designarena","metric":"design_code_overall_elo_battles","value":35541,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5-mini","source":"designarena","metric":"design_code_overall_elo","value":1115,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5-mini","source":"designarena","metric":"design_code_overall_elo_battles","value":37097,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-chat","source":"designarena","metric":"design_code_overall_elo","value":1108,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-chat","source":"designarena","metric":"design_code_overall_elo_battles","value":19271,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1-codex-mini","source":"designarena","metric":"design_code_overall_elo","value":1094,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1-codex-mini","source":"designarena","metric":"design_code_overall_elo_battles","value":33839,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5-nano","source":"designarena","metric":"design_code_overall_elo","value":1085,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5-nano","source":"designarena","metric":"design_code_overall_elo_battles","value":6703,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"designarena","metric":"design_code_overall_elo","value":1072,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"designarena","metric":"design_code_overall_elo_battles","value":23538,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3","source":"designarena","metric":"design_code_overall_elo","value":1069,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3","source":"designarena","metric":"design_code_overall_elo_battles","value":6390,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/ministral-14b-2512","source":"designarena","metric":"design_code_overall_elo","value":1065,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/ministral-14b-2512","source":"designarena","metric":"design_code_overall_elo_battles","value":2380,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-2.5-flash","source":"designarena","metric":"design_code_overall_elo","value":1059,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-2.5-flash","source":"designarena","metric":"design_code_overall_elo_battles","value":6971,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/ministral-8b-2512","source":"designarena","metric":"design_code_overall_elo","value":1053,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/ministral-8b-2512","source":"designarena","metric":"design_code_overall_elo_battles","value":2427,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"designarena","metric":"design_code_overall_elo","value":1039,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-235b-a22b-2507","source":"designarena","metric":"design_code_overall_elo_battles","value":6939,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2","source":"designarena","metric":"design_code_overall_elo","value":1034,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2","source":"designarena","metric":"design_code_overall_elo_battles","value":1352,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"designarena","metric":"design_code_overall_elo","value":1033,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"designarena","metric":"design_code_overall_elo_battles","value":6175,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4.1","source":"designarena","metric":"design_code_overall_elo","value":1026,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4.1","source":"designarena","metric":"design_code_overall_elo_battles","value":1747,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"inception/mercury-2","source":"designarena","metric":"design_code_overall_elo","value":1022,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"inception/mercury-2","source":"designarena","metric":"design_code_overall_elo_battles","value":25187,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/ministral-3b-2512","source":"designarena","metric":"design_code_overall_elo","value":1010,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/ministral-3b-2512","source":"designarena","metric":"design_code_overall_elo_battles","value":2852,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/codestral-2508","source":"designarena","metric":"design_code_overall_elo","value":1007,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/codestral-2508","source":"designarena","metric":"design_code_overall_elo_battles","value":6734,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4.1-mini","source":"designarena","metric":"design_code_overall_elo","value":994,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4.1-mini","source":"designarena","metric":"design_code_overall_elo_battles","value":1566,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-oss-120b","source":"designarena","metric":"design_code_overall_elo","value":963,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-oss-120b","source":"designarena","metric":"design_code_overall_elo_battles","value":5272,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4.1-nano","source":"designarena","metric":"design_code_overall_elo","value":963,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4.1-nano","source":"designarena","metric":"design_code_overall_elo_battles","value":1901,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-30b-a3b","source":"designarena","metric":"design_code_overall_elo","value":942,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-30b-a3b","source":"designarena","metric":"design_code_overall_elo_battles","value":2568,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta-llama/llama-4-maverick","source":"designarena","metric":"design_code_overall_elo","value":880,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta-llama/llama-4-maverick","source":"designarena","metric":"design_code_overall_elo_battles","value":1678,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4o","source":"designarena","metric":"design_code_overall_elo","value":861,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4o","source":"designarena","metric":"design_code_overall_elo_battles","value":1780,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta-llama/llama-4-scout","source":"designarena","metric":"design_code_overall_elo","value":790,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta-llama/llama-4-scout","source":"designarena","metric":"design_code_overall_elo_battles","value":1275,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-astra","source":"designarena","metric":"design_svg_elo","value":1431,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-astra","source":"designarena","metric":"design_svg_elo_battles","value":1626,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5.5","source":"designarena","metric":"design_svg_elo","value":1332,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5.5","source":"designarena","metric":"design_svg_elo_battles","value":998,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-sol","source":"designarena","metric":"design_svg_elo","value":1323,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-sol","source":"designarena","metric":"design_svg_elo_battles","value":577,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-sol","source":"designarena","metric":"design_svg_elo","value":1316,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-sol","source":"designarena","metric":"design_svg_elo_battles","value":1205,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5","source":"designarena","metric":"design_svg_elo","value":1310,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5","source":"designarena","metric":"design_svg_elo_battles","value":1700,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5","source":"designarena","metric":"design_svg_elo","value":1302,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5","source":"designarena","metric":"design_svg_elo_battles","value":2098,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.3","source":"designarena","metric":"design_svg_elo","value":1301,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.3","source":"designarena","metric":"design_svg_elo_battles","value":1385,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5.1","source":"designarena","metric":"design_svg_elo","value":1300,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5.1","source":"designarena","metric":"design_svg_elo_battles","value":1326,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k3","source":"designarena","metric":"design_svg_elo","value":1300,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k3","source":"designarena","metric":"design_svg_elo_battles","value":1070,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.8-flash","source":"designarena","metric":"design_svg_elo","value":1294,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.8-flash","source":"designarena","metric":"design_svg_elo_battles","value":2224,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.2","source":"designarena","metric":"design_svg_elo","value":1285,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.2","source":"designarena","metric":"design_svg_elo_battles","value":2080,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-pro-preview","source":"designarena","metric":"design_svg_elo","value":1284,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-pro-preview","source":"designarena","metric":"design_svg_elo_battles","value":4620,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.7-flash","source":"designarena","metric":"design_svg_elo","value":1283,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.7-flash","source":"designarena","metric":"design_svg_elo_battles","value":3551,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.5-flash","source":"designarena","metric":"design_svg_elo","value":1253,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.5-flash","source":"designarena","metric":"design_svg_elo_battles","value":3389,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-luna","source":"designarena","metric":"design_svg_elo","value":1251,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-luna","source":"designarena","metric":"design_svg_elo_battles","value":626,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"designarena","metric":"design_svg_elo","value":1243,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"designarena","metric":"design_svg_elo_battles","value":1010,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.5","source":"designarena","metric":"design_svg_elo","value":1234,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.5","source":"designarena","metric":"design_svg_elo_battles","value":3246,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-large-4-0","source":"designarena","metric":"design_svg_elo","value":1232,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-large-4-0","source":"designarena","metric":"design_svg_elo_battles","value":939,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.6","source":"designarena","metric":"design_svg_elo","value":1227,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.6","source":"designarena","metric":"design_svg_elo_battles","value":3987,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-terra","source":"designarena","metric":"design_svg_elo","value":1220,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-terra","source":"designarena","metric":"design_svg_elo_battles","value":6338,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-max","source":"designarena","metric":"design_svg_elo","value":1215,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-max","source":"designarena","metric":"design_svg_elo_battles","value":3770,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.2","source":"designarena","metric":"design_svg_elo","value":1214,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.2","source":"designarena","metric":"design_svg_elo_battles","value":2151,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-plus","source":"designarena","metric":"design_svg_elo","value":1206,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-plus","source":"designarena","metric":"design_svg_elo_battles","value":1429,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5-turbo","source":"designarena","metric":"design_svg_elo","value":1205,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5-turbo","source":"designarena","metric":"design_svg_elo_battles","value":4553,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"tencent/hy3","source":"designarena","metric":"design_svg_elo","value":1199,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"tencent/hy3","source":"designarena","metric":"design_svg_elo_battles","value":1089,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.6","source":"designarena","metric":"design_svg_elo","value":1196,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.6","source":"designarena","metric":"design_svg_elo_battles","value":4025,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-luna","source":"designarena","metric":"design_svg_elo","value":1194,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-luna","source":"designarena","metric":"design_svg_elo_battles","value":1549,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.8","source":"designarena","metric":"design_svg_elo","value":1193,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.8","source":"designarena","metric":"design_svg_elo_battles","value":2872,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5","source":"designarena","metric":"design_svg_elo","value":1193,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5","source":"designarena","metric":"design_svg_elo_battles","value":2574,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5","source":"designarena","metric":"design_svg_elo","value":1188,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5","source":"designarena","metric":"design_svg_elo_battles","value":1688,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"designarena","metric":"design_svg_elo","value":1184,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"designarena","metric":"design_svg_elo_battles","value":703,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.5","source":"designarena","metric":"design_svg_elo","value":1180,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.5","source":"designarena","metric":"design_svg_elo_battles","value":4787,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.6","source":"designarena","metric":"design_svg_elo","value":1180,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.6","source":"designarena","metric":"design_svg_elo_battles","value":3539,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"designarena","metric":"design_svg_elo","value":1180,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"designarena","metric":"design_svg_elo_battles","value":1693,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.5","source":"designarena","metric":"design_svg_elo","value":1177,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.5","source":"designarena","metric":"design_svg_elo_battles","value":2415,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.7-code","source":"designarena","metric":"design_svg_elo","value":1175,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.7-code","source":"designarena","metric":"design_svg_elo_battles","value":1839,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5","source":"designarena","metric":"design_svg_elo","value":1167,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5","source":"designarena","metric":"design_svg_elo_battles","value":7458,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m3","source":"designarena","metric":"design_svg_elo","value":1161,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m3","source":"designarena","metric":"design_svg_elo_battles","value":2593,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.6-plus","source":"designarena","metric":"design_svg_elo","value":1160,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.6-plus","source":"designarena","metric":"design_svg_elo_battles","value":5375,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-flash","source":"designarena","metric":"design_svg_elo","value":1154,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-flash","source":"designarena","metric":"design_svg_elo_battles","value":1990,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.1","source":"designarena","metric":"design_svg_elo","value":1151,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.1","source":"designarena","metric":"design_svg_elo_battles","value":1526,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5v-turbo","source":"designarena","metric":"design_svg_elo","value":1150,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5v-turbo","source":"designarena","metric":"design_svg_elo_battles","value":4996,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1","source":"designarena","metric":"design_svg_elo","value":1148,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1","source":"designarena","metric":"design_svg_elo_battles","value":2722,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.5","source":"designarena","metric":"design_svg_elo","value":1148,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.5","source":"designarena","metric":"design_svg_elo_battles","value":1549,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7","source":"designarena","metric":"design_svg_elo","value":1142,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7","source":"designarena","metric":"design_svg_elo_battles","value":7652,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.4","source":"designarena","metric":"design_svg_elo","value":1141,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.4","source":"designarena","metric":"design_svg_elo_battles","value":3842,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-pro","source":"designarena","metric":"design_svg_elo","value":1139,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-pro","source":"designarena","metric":"design_svg_elo_battles","value":2058,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"designarena","metric":"design_svg_elo","value":1138,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.5-397b-a17b","source":"designarena","metric":"design_svg_elo_battles","value":969,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2.1","source":"designarena","metric":"design_svg_elo","value":1130,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2.1","source":"designarena","metric":"design_svg_elo_battles","value":2075,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.3-codex","source":"designarena","metric":"design_svg_elo","value":1128,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.3-codex","source":"designarena","metric":"design_svg_elo_battles","value":3026,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.5","source":"designarena","metric":"design_svg_elo","value":1114,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.5","source":"designarena","metric":"design_svg_elo_battles","value":5117,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"thinkingmachines/inkling","source":"designarena","metric":"design_svg_elo","value":1110,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"thinkingmachines/inkling","source":"designarena","metric":"design_svg_elo_battles","value":1282,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.6","source":"designarena","metric":"design_svg_elo","value":1108,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.6","source":"designarena","metric":"design_svg_elo_battles","value":1920,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.5-plus-02-15","source":"designarena","metric":"design_svg_elo","value":1107,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.5-plus-02-15","source":"designarena","metric":"design_svg_elo_battles","value":3352,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.5","source":"designarena","metric":"design_svg_elo","value":1095,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.5","source":"designarena","metric":"design_svg_elo_battles","value":1961,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5-mini","source":"designarena","metric":"design_svg_elo","value":1090,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5-mini","source":"designarena","metric":"design_svg_elo_battles","value":4694,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"stepfun/step-3.7-flash","source":"designarena","metric":"design_svg_elo","value":1083,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"stepfun/step-3.7-flash","source":"designarena","metric":"design_svg_elo_battles","value":2164,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.3","source":"designarena","metric":"design_svg_elo","value":1081,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.3","source":"designarena","metric":"design_svg_elo_battles","value":3416,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.5-air","source":"designarena","metric":"design_svg_elo","value":1070,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.5-air","source":"designarena","metric":"design_svg_elo_battles","value":1639,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"designarena","metric":"design_svg_elo","value":1068,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"designarena","metric":"design_svg_elo_battles","value":2153,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"designarena","metric":"design_svg_elo","value":1051,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"designarena","metric":"design_svg_elo_battles","value":3753,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-r1-0528","source":"designarena","metric":"design_svg_elo","value":1038,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-r1-0528","source":"designarena","metric":"design_svg_elo_battles","value":1568,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7-flash","source":"designarena","metric":"design_svg_elo","value":1037,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7-flash","source":"designarena","metric":"design_svg_elo_battles","value":1587,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.2","source":"designarena","metric":"design_svg_elo","value":1031,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.2","source":"designarena","metric":"design_svg_elo_battles","value":4611,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"designarena","metric":"design_svg_elo","value":1031,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.2-exp","source":"designarena","metric":"design_svg_elo_battles","value":2352,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-haiku-4.5","source":"designarena","metric":"design_svg_elo","value":1025,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-haiku-4.5","source":"designarena","metric":"design_svg_elo_battles","value":4714,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"arcee-ai/trinity-large-thinking","source":"designarena","metric":"design_svg_elo","value":1015,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"arcee-ai/trinity-large-thinking","source":"designarena","metric":"design_svg_elo_battles","value":2774,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"inception/mercury-2","source":"designarena","metric":"design_svg_elo","value":997,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"inception/mercury-2","source":"designarena","metric":"design_svg_elo_battles","value":1713,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-large-2512","source":"designarena","metric":"design_svg_elo","value":992,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-large-2512","source":"designarena","metric":"design_svg_elo_battles","value":4910,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3.1","source":"designarena","metric":"design_svg_elo","value":992,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3.1","source":"designarena","metric":"design_svg_elo_battles","value":4843,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1-codex-mini","source":"designarena","metric":"design_svg_elo","value":977,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1-codex-mini","source":"designarena","metric":"design_svg_elo_battles","value":4888,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-chat","source":"designarena","metric":"design_svg_elo","value":975,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-chat","source":"designarena","metric":"design_svg_elo_battles","value":1708,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3-5","source":"designarena","metric":"design_svg_elo","value":948,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3-5","source":"designarena","metric":"design_svg_elo_battles","value":1157,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-astra","source":"designarena","metric":"design_ascii_art_elo","value":1356,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-astra","source":"designarena","metric":"design_ascii_art_elo_battles","value":167,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5","source":"designarena","metric":"design_ascii_art_elo","value":1352,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5","source":"designarena","metric":"design_ascii_art_elo_battles","value":227,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5","source":"designarena","metric":"design_ascii_art_elo","value":1329,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5","source":"designarena","metric":"design_ascii_art_elo_battles","value":298,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5.1","source":"designarena","metric":"design_ascii_art_elo","value":1323,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5.1","source":"designarena","metric":"design_ascii_art_elo_battles","value":137,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-sol","source":"designarena","metric":"design_ascii_art_elo","value":1300,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-sol","source":"designarena","metric":"design_ascii_art_elo_battles","value":246,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.2","source":"designarena","metric":"design_ascii_art_elo","value":1284,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.2","source":"designarena","metric":"design_ascii_art_elo_battles","value":550,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.3","source":"designarena","metric":"design_ascii_art_elo","value":1283,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.3","source":"designarena","metric":"design_ascii_art_elo_battles","value":214,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.6-flash","source":"designarena","metric":"design_ascii_art_elo","value":1279,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.6-flash","source":"designarena","metric":"design_ascii_art_elo_battles","value":352,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.8","source":"designarena","metric":"design_ascii_art_elo","value":1277,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.8","source":"designarena","metric":"design_ascii_art_elo_battles","value":443,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.7-flash","source":"designarena","metric":"design_ascii_art_elo","value":1276,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.7-flash","source":"designarena","metric":"design_ascii_art_elo_battles","value":545,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-pro-preview","source":"designarena","metric":"design_ascii_art_elo","value":1270,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-pro-preview","source":"designarena","metric":"design_ascii_art_elo_battles","value":1358,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"designarena","metric":"design_ascii_art_elo","value":1265,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4.1-flash","source":"designarena","metric":"design_ascii_art_elo_battles","value":288,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.8-flash","source":"designarena","metric":"design_ascii_art_elo","value":1262,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.8-flash","source":"designarena","metric":"design_ascii_art_elo_battles","value":267,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.5","source":"designarena","metric":"design_ascii_art_elo","value":1256,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.5","source":"designarena","metric":"design_ascii_art_elo_battles","value":550,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.6","source":"designarena","metric":"design_ascii_art_elo","value":1255,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.6","source":"designarena","metric":"design_ascii_art_elo_battles","value":412,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.5-flash","source":"designarena","metric":"design_ascii_art_elo","value":1254,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.5-flash","source":"designarena","metric":"design_ascii_art_elo_battles","value":1384,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.6","source":"designarena","metric":"design_ascii_art_elo","value":1236,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.6","source":"designarena","metric":"design_ascii_art_elo_battles","value":411,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-sol","source":"designarena","metric":"design_ascii_art_elo","value":1223,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-sol","source":"designarena","metric":"design_ascii_art_elo_battles","value":239,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-max","source":"designarena","metric":"design_ascii_art_elo","value":1212,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-max","source":"designarena","metric":"design_ascii_art_elo_battles","value":788,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5","source":"designarena","metric":"design_ascii_art_elo","value":1208,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5","source":"designarena","metric":"design_ascii_art_elo_battles","value":701,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.5","source":"designarena","metric":"design_ascii_art_elo","value":1205,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.5","source":"designarena","metric":"design_ascii_art_elo_battles","value":531,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-large-4-0","source":"designarena","metric":"design_ascii_art_elo","value":1202,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-large-4-0","source":"designarena","metric":"design_ascii_art_elo_battles","value":161,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.8-max-0902","source":"designarena","metric":"design_ascii_art_elo","value":1199,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.8-max-0902","source":"designarena","metric":"design_ascii_art_elo_battles","value":246,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.7-code","source":"designarena","metric":"design_ascii_art_elo","value":1198,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.7-code","source":"designarena","metric":"design_ascii_art_elo_battles","value":502,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.2","source":"designarena","metric":"design_ascii_art_elo","value":1192,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.2","source":"designarena","metric":"design_ascii_art_elo_battles","value":581,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.5","source":"designarena","metric":"design_ascii_art_elo","value":1190,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.5","source":"designarena","metric":"design_ascii_art_elo_battles","value":429,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.4","source":"designarena","metric":"design_ascii_art_elo","value":1189,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.4","source":"designarena","metric":"design_ascii_art_elo_battles","value":1310,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-terra","source":"designarena","metric":"design_ascii_art_elo","value":1178,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-terra","source":"designarena","metric":"design_ascii_art_elo_battles","value":1415,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.1","source":"designarena","metric":"design_ascii_art_elo","value":1167,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.1","source":"designarena","metric":"design_ascii_art_elo_battles","value":458,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"designarena","metric":"design_ascii_art_elo","value":1167,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-flash-lite-preview","source":"designarena","metric":"design_ascii_art_elo_battles","value":1211,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.5","source":"designarena","metric":"design_ascii_art_elo","value":1166,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.5","source":"designarena","metric":"design_ascii_art_elo_battles","value":931,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7","source":"designarena","metric":"design_ascii_art_elo","value":1165,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7","source":"designarena","metric":"design_ascii_art_elo_battles","value":1137,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.6","source":"designarena","metric":"design_ascii_art_elo","value":1165,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.6","source":"designarena","metric":"design_ascii_art_elo_battles","value":120,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m3","source":"designarena","metric":"design_ascii_art_elo","value":1161,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m3","source":"designarena","metric":"design_ascii_art_elo_battles","value":500,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5-turbo","source":"designarena","metric":"design_ascii_art_elo","value":1159,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5-turbo","source":"designarena","metric":"design_ascii_art_elo_battles","value":395,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"designarena","metric":"design_ascii_art_elo","value":1157,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.5-pro","source":"designarena","metric":"design_ascii_art_elo_battles","value":262,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-luna","source":"designarena","metric":"design_ascii_art_elo","value":1157,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-luna","source":"designarena","metric":"design_ascii_art_elo_battles","value":275,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"tencent/hy3","source":"designarena","metric":"design_ascii_art_elo","value":1157,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"tencent/hy3","source":"designarena","metric":"design_ascii_art_elo_battles","value":201,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"stepfun/step-3.7-flash","source":"designarena","metric":"design_ascii_art_elo","value":1153,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"stepfun/step-3.7-flash","source":"designarena","metric":"design_ascii_art_elo_battles","value":609,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.3-codex","source":"designarena","metric":"design_ascii_art_elo","value":1152,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.3-codex","source":"designarena","metric":"design_ascii_art_elo_battles","value":258,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-pro","source":"designarena","metric":"design_ascii_art_elo","value":1149,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-pro","source":"designarena","metric":"design_ascii_art_elo_battles","value":679,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5","source":"designarena","metric":"design_ascii_art_elo","value":1147,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5","source":"designarena","metric":"design_ascii_art_elo_battles","value":984,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-luna","source":"designarena","metric":"design_ascii_art_elo","value":1144,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-luna","source":"designarena","metric":"design_ascii_art_elo_battles","value":316,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-plus","source":"designarena","metric":"design_ascii_art_elo","value":1144,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-plus","source":"designarena","metric":"design_ascii_art_elo_battles","value":254,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.5","source":"designarena","metric":"design_ascii_art_elo","value":1142,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.5","source":"designarena","metric":"design_ascii_art_elo_battles","value":359,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5","source":"designarena","metric":"design_ascii_art_elo","value":1141,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5","source":"designarena","metric":"design_ascii_art_elo_battles","value":312,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-haiku-4.5","source":"designarena","metric":"design_ascii_art_elo","value":1140,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-haiku-4.5","source":"designarena","metric":"design_ascii_art_elo_battles","value":353,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.3","source":"designarena","metric":"design_ascii_art_elo","value":1126,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.3","source":"designarena","metric":"design_ascii_art_elo_battles","value":600,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5-mini","source":"designarena","metric":"design_ascii_art_elo","value":1124,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5-mini","source":"designarena","metric":"design_ascii_art_elo_battles","value":414,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5v-turbo","source":"designarena","metric":"design_ascii_art_elo","value":1119,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5v-turbo","source":"designarena","metric":"design_ascii_art_elo_battles","value":477,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1","source":"designarena","metric":"design_ascii_art_elo","value":1119,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1","source":"designarena","metric":"design_ascii_art_elo_battles","value":140,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.6-plus","source":"designarena","metric":"design_ascii_art_elo","value":1116,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.6-plus","source":"designarena","metric":"design_ascii_art_elo_battles","value":456,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-flash","source":"designarena","metric":"design_ascii_art_elo","value":1111,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-flash","source":"designarena","metric":"design_ascii_art_elo_battles","value":297,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1-codex-mini","source":"designarena","metric":"design_ascii_art_elo","value":1105,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1-codex-mini","source":"designarena","metric":"design_ascii_art_elo_battles","value":309,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"designarena","metric":"design_ascii_art_elo","value":1098,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"nvidia/nemotron-3-ultra-550b-a55b","source":"designarena","metric":"design_ascii_art_elo_battles","value":289,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.5-plus-02-15","source":"designarena","metric":"design_ascii_art_elo","value":1094,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.5-plus-02-15","source":"designarena","metric":"design_ascii_art_elo_battles","value":296,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"designarena","metric":"design_ascii_art_elo","value":1091,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-flash-0731","source":"designarena","metric":"design_ascii_art_elo_battles","value":105,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"thinkingmachines/inkling","source":"designarena","metric":"design_ascii_art_elo","value":1089,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"thinkingmachines/inkling","source":"designarena","metric":"design_ascii_art_elo_battles","value":220,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.2","source":"designarena","metric":"design_ascii_art_elo","value":1083,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.2","source":"designarena","metric":"design_ascii_art_elo_battles","value":259,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-large-2512","source":"designarena","metric":"design_ascii_art_elo","value":1069,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-large-2512","source":"designarena","metric":"design_ascii_art_elo_battles","value":340,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3-5","source":"designarena","metric":"design_ascii_art_elo","value":1063,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3-5","source":"designarena","metric":"design_ascii_art_elo_battles","value":205,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"arcee-ai/trinity-large-thinking","source":"designarena","metric":"design_ascii_art_elo","value":1042,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"arcee-ai/trinity-large-thinking","source":"designarena","metric":"design_ascii_art_elo_battles","value":116,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3.1","source":"designarena","metric":"design_ascii_art_elo","value":998,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-medium-3.1","source":"designarena","metric":"design_ascii_art_elo_battles","value":357,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"inception/mercury-2","source":"designarena","metric":"design_ascii_art_elo","value":993,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"inception/mercury-2","source":"designarena","metric":"design_ascii_art_elo_battles","value":210,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-astra","source":"designarena","metric":"design_agents_webapps_elo","value":1373,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-astra","source":"designarena","metric":"design_agents_webapps_elo_battles","value":650,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5.1","source":"designarena","metric":"design_agents_webapps_elo","value":1318,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5.1","source":"designarena","metric":"design_agents_webapps_elo_battles","value":745,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5.5","source":"designarena","metric":"design_agents_webapps_elo","value":1318,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5.5","source":"designarena","metric":"design_agents_webapps_elo_battles","value":507,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.8-max-0902","source":"designarena","metric":"design_agents_webapps_elo","value":1298,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.8-max-0902","source":"designarena","metric":"design_agents_webapps_elo_battles","value":1756,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.3","source":"designarena","metric":"design_agents_webapps_elo","value":1296,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.3","source":"designarena","metric":"design_agents_webapps_elo_battles","value":5087,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k3","source":"designarena","metric":"design_agents_webapps_elo","value":1293,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k3","source":"designarena","metric":"design_agents_webapps_elo_battles","value":1916,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5","source":"designarena","metric":"design_agents_webapps_elo","value":1266,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5","source":"designarena","metric":"design_agents_webapps_elo_battles","value":1860,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5","source":"designarena","metric":"design_agents_webapps_elo","value":1261,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5","source":"designarena","metric":"design_agents_webapps_elo_battles","value":2911,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-sol","source":"designarena","metric":"design_agents_webapps_elo","value":1248,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-sol","source":"designarena","metric":"design_agents_webapps_elo_battles","value":2524,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5","source":"designarena","metric":"design_agents_webapps_elo","value":1246,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5","source":"designarena","metric":"design_agents_webapps_elo_battles","value":4597,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.8-flash","source":"designarena","metric":"design_agents_webapps_elo","value":1236,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.8-flash","source":"designarena","metric":"design_agents_webapps_elo_battles","value":1433,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.8","source":"designarena","metric":"design_agents_webapps_elo","value":1232,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.8","source":"designarena","metric":"design_agents_webapps_elo_battles","value":3664,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-sol","source":"designarena","metric":"design_agents_webapps_elo","value":1226,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-sol","source":"designarena","metric":"design_agents_webapps_elo_battles","value":582,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.2","source":"designarena","metric":"design_agents_webapps_elo","value":1222,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.2","source":"designarena","metric":"design_agents_webapps_elo_battles","value":6292,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.7-flash","source":"designarena","metric":"design_agents_webapps_elo","value":1221,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.7-flash","source":"designarena","metric":"design_agents_webapps_elo_battles","value":1236,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.2","source":"designarena","metric":"design_agents_webapps_elo","value":1221,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.2","source":"designarena","metric":"design_agents_webapps_elo_battles","value":2039,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-max","source":"designarena","metric":"design_agents_webapps_elo","value":1210,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-max","source":"designarena","metric":"design_agents_webapps_elo_battles","value":2909,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.6","source":"designarena","metric":"design_agents_webapps_elo","value":1206,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.6","source":"designarena","metric":"design_agents_webapps_elo_battles","value":4135,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.5-flash","source":"designarena","metric":"design_agents_webapps_elo","value":1202,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.5-flash","source":"designarena","metric":"design_agents_webapps_elo_battles","value":5699,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m3","source":"designarena","metric":"design_agents_webapps_elo","value":1198,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m3","source":"designarena","metric":"design_agents_webapps_elo_battles","value":3567,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"thinkingmachines/inkling","source":"designarena","metric":"design_agents_webapps_elo","value":1196,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"thinkingmachines/inkling","source":"designarena","metric":"design_agents_webapps_elo_battles","value":1207,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.6-flash","source":"designarena","metric":"design_agents_webapps_elo","value":1195,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.6-flash","source":"designarena","metric":"design_agents_webapps_elo_battles","value":2809,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-luna","source":"designarena","metric":"design_agents_webapps_elo","value":1193,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-luna","source":"designarena","metric":"design_agents_webapps_elo_battles","value":552,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.6","source":"designarena","metric":"design_agents_webapps_elo","value":1190,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.6","source":"designarena","metric":"design_agents_webapps_elo_battles","value":2825,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.7-code","source":"designarena","metric":"design_agents_webapps_elo","value":1176,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.7-code","source":"designarena","metric":"design_agents_webapps_elo_battles","value":4373,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.1","source":"designarena","metric":"design_agents_webapps_elo","value":1175,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.1","source":"designarena","metric":"design_agents_webapps_elo_battles","value":7155,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.5","source":"designarena","metric":"design_agents_webapps_elo","value":1159,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.5","source":"designarena","metric":"design_agents_webapps_elo_battles","value":2697,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.5","source":"designarena","metric":"design_agents_webapps_elo","value":1136,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.5","source":"designarena","metric":"design_agents_webapps_elo_battles","value":3435,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-pro-preview","source":"designarena","metric":"design_agents_webapps_elo","value":1126,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-pro-preview","source":"designarena","metric":"design_agents_webapps_elo_battles","value":6609,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.3","source":"designarena","metric":"design_agents_webapps_elo","value":1126,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.3","source":"designarena","metric":"design_agents_webapps_elo_battles","value":6416,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5v-turbo","source":"designarena","metric":"design_agents_webapps_elo","value":1124,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5v-turbo","source":"designarena","metric":"design_agents_webapps_elo_battles","value":5385,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-terra","source":"designarena","metric":"design_agents_webapps_elo","value":1120,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-terra","source":"designarena","metric":"design_agents_webapps_elo_battles","value":3489,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.5","source":"designarena","metric":"design_agents_webapps_elo","value":1117,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.5","source":"designarena","metric":"design_agents_webapps_elo_battles","value":5341,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3-flash-preview","source":"designarena","metric":"design_agents_webapps_elo","value":1111,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3-flash-preview","source":"designarena","metric":"design_agents_webapps_elo_battles","value":3979,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"upstage/solar-pro4","source":"designarena","metric":"design_agents_webapps_elo","value":1105,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"upstage/solar-pro4","source":"designarena","metric":"design_agents_webapps_elo_battles","value":1315,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.2","source":"designarena","metric":"design_agents_webapps_elo","value":1086,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.2","source":"designarena","metric":"design_agents_webapps_elo_battles","value":3570,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.5","source":"designarena","metric":"design_agents_webapps_elo","value":1060,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.5","source":"designarena","metric":"design_agents_webapps_elo_battles","value":1503,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.4","source":"designarena","metric":"design_agents_webapps_elo","value":1059,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.4","source":"designarena","metric":"design_agents_webapps_elo_battles","value":3319,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.2-codex","source":"designarena","metric":"design_agents_webapps_elo","value":1051,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.2-codex","source":"designarena","metric":"design_agents_webapps_elo_battles","value":3426,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.3-codex","source":"designarena","metric":"design_agents_webapps_elo","value":1032,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.3-codex","source":"designarena","metric":"design_agents_webapps_elo_battles","value":2245,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1-codex","source":"designarena","metric":"design_agents_webapps_elo","value":1018,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1-codex","source":"designarena","metric":"design_agents_webapps_elo_battles","value":525,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-astra","source":"designarena","metric":"design_agents_fullstack_elo","value":1357,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-astra","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":553,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5.1","source":"designarena","metric":"design_agents_fullstack_elo","value":1326,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5.1","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":509,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k3","source":"designarena","metric":"design_agents_fullstack_elo","value":1315,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k3","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":1316,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5","source":"designarena","metric":"design_agents_fullstack_elo","value":1306,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":1195,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.8-max-0902","source":"designarena","metric":"design_agents_fullstack_elo","value":1305,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.8-max-0902","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":1327,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.3","source":"designarena","metric":"design_agents_fullstack_elo","value":1295,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.3","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":4009,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5","source":"designarena","metric":"design_agents_fullstack_elo","value":1280,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":2118,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-sol","source":"designarena","metric":"design_agents_fullstack_elo","value":1261,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-sol","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":1977,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5","source":"designarena","metric":"design_agents_fullstack_elo","value":1249,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":3746,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.8","source":"designarena","metric":"design_agents_fullstack_elo","value":1249,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.8","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":2700,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.8-flash","source":"designarena","metric":"design_agents_fullstack_elo","value":1244,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.8-flash","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":1155,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.2","source":"designarena","metric":"design_agents_fullstack_elo","value":1241,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.2","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":2760,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-sol","source":"designarena","metric":"design_agents_fullstack_elo","value":1238,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-sol","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":1172,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.6","source":"designarena","metric":"design_agents_fullstack_elo","value":1220,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.6","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":2517,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.6","source":"designarena","metric":"design_agents_fullstack_elo","value":1213,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.6","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":2030,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.2","source":"designarena","metric":"design_agents_fullstack_elo","value":1210,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.2","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":1907,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.7-flash","source":"designarena","metric":"design_agents_fullstack_elo","value":1209,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.7-flash","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":682,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.5-flash","source":"designarena","metric":"design_agents_fullstack_elo","value":1197,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.5-flash","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":4032,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m3","source":"designarena","metric":"design_agents_fullstack_elo","value":1197,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m3","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":3673,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-max","source":"designarena","metric":"design_agents_fullstack_elo","value":1191,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-max","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":1417,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.6-flash","source":"designarena","metric":"design_agents_fullstack_elo","value":1181,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.6-flash","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":2934,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.7-code","source":"designarena","metric":"design_agents_fullstack_elo","value":1175,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.7-code","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":2794,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.1","source":"designarena","metric":"design_agents_fullstack_elo","value":1167,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.1","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":3901,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-luna","source":"designarena","metric":"design_agents_fullstack_elo","value":1158,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-luna","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":1052,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.5","source":"designarena","metric":"design_agents_fullstack_elo","value":1156,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.5","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":1396,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.6","source":"designarena","metric":"design_agents_fullstack_elo","value":1155,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.6","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":5980,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5v-turbo","source":"designarena","metric":"design_agents_fullstack_elo","value":1149,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5v-turbo","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":3947,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5","source":"designarena","metric":"design_agents_fullstack_elo","value":1123,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":4765,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.5","source":"designarena","metric":"design_agents_fullstack_elo","value":1114,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.5","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":1787,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.5","source":"designarena","metric":"design_agents_fullstack_elo","value":1089,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.5","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":3539,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-pro-preview","source":"designarena","metric":"design_agents_fullstack_elo","value":1068,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-pro-preview","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":4827,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3-flash-preview","source":"designarena","metric":"design_agents_fullstack_elo","value":1063,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3-flash-preview","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":2359,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-terra","source":"designarena","metric":"design_agents_fullstack_elo","value":1061,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-terra","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":2589,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.5","source":"designarena","metric":"design_agents_fullstack_elo","value":1050,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.5","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":629,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7","source":"designarena","metric":"design_agents_fullstack_elo","value":1050,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":1639,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.2","source":"designarena","metric":"design_agents_fullstack_elo","value":1043,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.2","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":2165,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.6","source":"designarena","metric":"design_agents_fullstack_elo","value":1029,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.6","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":1885,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.4","source":"designarena","metric":"design_agents_fullstack_elo","value":1017,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.4","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":2152,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.3","source":"designarena","metric":"design_agents_fullstack_elo","value":1006,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.3","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":3448,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.2-codex","source":"designarena","metric":"design_agents_fullstack_elo","value":993,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.2-codex","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":2158,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.3-codex","source":"designarena","metric":"design_agents_fullstack_elo","value":983,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.3-codex","source":"designarena","metric":"design_agents_fullstack_elo_battles","value":1110,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5.5","source":"designarena","metric":"design_agents_mobileapps_elo","value":1323,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5.5","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":610,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-astra","source":"designarena","metric":"design_agents_mobileapps_elo","value":1308,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-astra","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":588,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5.5","source":"designarena","metric":"design_agents_mobileapps_elo","value":1272,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5.5","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":210,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k3","source":"designarena","metric":"design_agents_mobileapps_elo","value":1267,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k3","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":1106,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5.1","source":"designarena","metric":"design_agents_mobileapps_elo","value":1266,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5.1","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":481,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5","source":"designarena","metric":"design_agents_mobileapps_elo","value":1263,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":791,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-sol","source":"designarena","metric":"design_agents_mobileapps_elo","value":1250,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-sol","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":1098,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.8-flash","source":"designarena","metric":"design_agents_mobileapps_elo","value":1235,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.8-flash","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":4206,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-sol","source":"designarena","metric":"design_agents_mobileapps_elo","value":1233,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-sol","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":225,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.7-flash","source":"designarena","metric":"design_agents_mobileapps_elo","value":1227,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.7-flash","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":650,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.8","source":"designarena","metric":"design_agents_mobileapps_elo","value":1221,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.8","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":1254,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.8-max-0902","source":"designarena","metric":"design_agents_mobileapps_elo","value":1221,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.8-max-0902","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":1565,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.3","source":"designarena","metric":"design_agents_mobileapps_elo","value":1218,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.3","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":819,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5","source":"designarena","metric":"design_agents_mobileapps_elo","value":1214,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":1942,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.6","source":"designarena","metric":"design_agents_mobileapps_elo","value":1211,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.6","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":1558,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.6","source":"designarena","metric":"design_agents_mobileapps_elo","value":1206,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.6","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":2143,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6.1-sol","source":"designarena","metric":"design_agents_mobileapps_elo","value":1198,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6.1-sol","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":162,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.6-flash","source":"designarena","metric":"design_agents_mobileapps_elo","value":1197,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.6-flash","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":1724,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.3","source":"designarena","metric":"design_agents_mobileapps_elo","value":1193,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.3","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":301,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.5","source":"designarena","metric":"design_agents_mobileapps_elo","value":1188,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.5","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":1542,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.2","source":"designarena","metric":"design_agents_mobileapps_elo","value":1181,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.2","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":1265,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.5-flash","source":"designarena","metric":"design_agents_mobileapps_elo","value":1176,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.5-flash","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":1344,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m3","source":"designarena","metric":"design_agents_mobileapps_elo","value":1168,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m3","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":2154,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.1","source":"designarena","metric":"design_agents_mobileapps_elo","value":1161,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.1","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":3235,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.2","source":"designarena","metric":"design_agents_mobileapps_elo","value":1159,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.2","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":1855,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.6","source":"designarena","metric":"design_agents_mobileapps_elo","value":1155,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.6","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":2665,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-max","source":"designarena","metric":"design_agents_mobileapps_elo","value":1151,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-max","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":1193,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.5","source":"designarena","metric":"design_agents_mobileapps_elo","value":1146,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.5","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":1391,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.5","source":"designarena","metric":"design_agents_mobileapps_elo","value":1142,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.5","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":843,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.7-code","source":"designarena","metric":"design_agents_mobileapps_elo","value":1142,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.7-code","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":1307,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.5","source":"designarena","metric":"design_agents_mobileapps_elo","value":1136,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.5","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":414,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5","source":"designarena","metric":"design_agents_mobileapps_elo","value":1135,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":2854,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5v-turbo","source":"designarena","metric":"design_agents_mobileapps_elo","value":1134,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5v-turbo","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":1601,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-luna","source":"designarena","metric":"design_agents_mobileapps_elo","value":1130,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-luna","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":156,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-terra","source":"designarena","metric":"design_agents_mobileapps_elo","value":1110,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-terra","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":1078,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7","source":"designarena","metric":"design_agents_mobileapps_elo","value":1104,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":1550,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.6","source":"designarena","metric":"design_agents_mobileapps_elo","value":1095,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.6","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":1660,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-pro-preview","source":"designarena","metric":"design_agents_mobileapps_elo","value":1093,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-pro-preview","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":2911,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.2","source":"designarena","metric":"design_agents_mobileapps_elo","value":1093,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.2","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":1813,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3-flash-preview","source":"designarena","metric":"design_agents_mobileapps_elo","value":1089,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3-flash-preview","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":2015,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.2-codex","source":"designarena","metric":"design_agents_mobileapps_elo","value":1089,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.2-codex","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":1767,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.4","source":"designarena","metric":"design_agents_mobileapps_elo","value":1086,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.4","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":1929,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.3","source":"designarena","metric":"design_agents_mobileapps_elo","value":1057,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.3","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":1616,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.3-codex","source":"designarena","metric":"design_agents_mobileapps_elo","value":1053,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.3-codex","source":"designarena","metric":"design_agents_mobileapps_elo_battles","value":955,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5","source":"designarena","metric":"design_agents_android_elo","value":1298,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5","source":"designarena","metric":"design_agents_android_elo_battles","value":461,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5","source":"designarena","metric":"design_agents_android_elo","value":1267,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5","source":"designarena","metric":"design_agents_android_elo_battles","value":389,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k3","source":"designarena","metric":"design_agents_android_elo","value":1263,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k3","source":"designarena","metric":"design_agents_android_elo_battles","value":455,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.7-flash","source":"designarena","metric":"design_agents_android_elo","value":1256,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.7-flash","source":"designarena","metric":"design_agents_android_elo_battles","value":2229,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-sol","source":"designarena","metric":"design_agents_android_elo","value":1255,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-sol","source":"designarena","metric":"design_agents_android_elo_battles","value":635,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.8","source":"designarena","metric":"design_agents_android_elo","value":1247,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.8","source":"designarena","metric":"design_agents_android_elo_battles","value":938,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5","source":"designarena","metric":"design_agents_android_elo","value":1239,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5","source":"designarena","metric":"design_agents_android_elo_battles","value":950,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.2","source":"designarena","metric":"design_agents_android_elo","value":1237,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.2","source":"designarena","metric":"design_agents_android_elo_battles","value":841,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.6-flash","source":"designarena","metric":"design_agents_android_elo","value":1218,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.6-flash","source":"designarena","metric":"design_agents_android_elo_battles","value":2300,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.6","source":"designarena","metric":"design_agents_android_elo","value":1214,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.6","source":"designarena","metric":"design_agents_android_elo_battles","value":778,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.6","source":"designarena","metric":"design_agents_android_elo","value":1212,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.6","source":"designarena","metric":"design_agents_android_elo_battles","value":1101,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.5-flash","source":"designarena","metric":"design_agents_android_elo","value":1200,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.5-flash","source":"designarena","metric":"design_agents_android_elo_battles","value":2407,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.1","source":"designarena","metric":"design_agents_android_elo","value":1195,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.1","source":"designarena","metric":"design_agents_android_elo_battles","value":1078,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.2","source":"designarena","metric":"design_agents_android_elo","value":1193,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.2","source":"designarena","metric":"design_agents_android_elo_battles","value":1529,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.5","source":"designarena","metric":"design_agents_android_elo","value":1192,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.5","source":"designarena","metric":"design_agents_android_elo_battles","value":661,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.5","source":"designarena","metric":"design_agents_android_elo","value":1178,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.5","source":"designarena","metric":"design_agents_android_elo_battles","value":1611,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.6","source":"designarena","metric":"design_agents_android_elo","value":1175,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.6","source":"designarena","metric":"design_agents_android_elo_battles","value":1665,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-max","source":"designarena","metric":"design_agents_android_elo","value":1174,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-max","source":"designarena","metric":"design_agents_android_elo_battles","value":753,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m3","source":"designarena","metric":"design_agents_android_elo","value":1173,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m3","source":"designarena","metric":"design_agents_android_elo_battles","value":1160,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5","source":"designarena","metric":"design_agents_android_elo","value":1162,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5","source":"designarena","metric":"design_agents_android_elo_battles","value":1602,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.7-code","source":"designarena","metric":"design_agents_android_elo","value":1152,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.7-code","source":"designarena","metric":"design_agents_android_elo_battles","value":658,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.5","source":"designarena","metric":"design_agents_android_elo","value":1135,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.5","source":"designarena","metric":"design_agents_android_elo_battles","value":554,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7","source":"designarena","metric":"design_agents_android_elo","value":1129,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7","source":"designarena","metric":"design_agents_android_elo_battles","value":421,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.6","source":"designarena","metric":"design_agents_android_elo","value":1101,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.6","source":"designarena","metric":"design_agents_android_elo_battles","value":500,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.8-flash","source":"designarena","metric":"design_agents_android_elo","value":1078,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.8-flash","source":"designarena","metric":"design_agents_android_elo_battles","value":323,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-terra","source":"designarena","metric":"design_agents_android_elo","value":1075,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-terra","source":"designarena","metric":"design_agents_android_elo_battles","value":1428,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.2","source":"designarena","metric":"design_agents_android_elo","value":1075,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.2","source":"designarena","metric":"design_agents_android_elo_battles","value":660,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3-flash-preview","source":"designarena","metric":"design_agents_android_elo","value":1067,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3-flash-preview","source":"designarena","metric":"design_agents_android_elo_battles","value":720,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-pro-preview","source":"designarena","metric":"design_agents_android_elo","value":1065,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-pro-preview","source":"designarena","metric":"design_agents_android_elo_battles","value":5361,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.4","source":"designarena","metric":"design_agents_android_elo","value":1047,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.4","source":"designarena","metric":"design_agents_android_elo_battles","value":502,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.3","source":"designarena","metric":"design_agents_android_elo","value":977,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.3","source":"designarena","metric":"design_agents_android_elo_battles","value":1812,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-astra","source":"designarena","metric":"design_agents_godot_elo","value":1348,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-astra","source":"designarena","metric":"design_agents_godot_elo_battles","value":328,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5.1","source":"designarena","metric":"design_agents_godot_elo","value":1327,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5.1","source":"designarena","metric":"design_agents_godot_elo_battles","value":629,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5","source":"designarena","metric":"design_agents_godot_elo","value":1292,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5","source":"designarena","metric":"design_agents_godot_elo_battles","value":1379,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5","source":"designarena","metric":"design_agents_godot_elo","value":1279,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5","source":"designarena","metric":"design_agents_godot_elo_battles","value":793,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.8-flash","source":"designarena","metric":"design_agents_godot_elo","value":1273,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.8-flash","source":"designarena","metric":"design_agents_godot_elo_battles","value":664,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.7-flash","source":"designarena","metric":"design_agents_godot_elo","value":1264,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.7-flash","source":"designarena","metric":"design_agents_godot_elo_battles","value":461,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-sol","source":"designarena","metric":"design_agents_godot_elo","value":1260,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-sol","source":"designarena","metric":"design_agents_godot_elo_battles","value":595,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.8-max-0902","source":"designarena","metric":"design_agents_godot_elo","value":1234,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.8-max-0902","source":"designarena","metric":"design_agents_godot_elo_battles","value":453,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.8","source":"designarena","metric":"design_agents_godot_elo","value":1231,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.8","source":"designarena","metric":"design_agents_godot_elo_battles","value":1659,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5","source":"designarena","metric":"design_agents_godot_elo","value":1225,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5","source":"designarena","metric":"design_agents_godot_elo_battles","value":1573,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k3","source":"designarena","metric":"design_agents_godot_elo","value":1223,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k3","source":"designarena","metric":"design_agents_godot_elo_battles","value":587,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-max","source":"designarena","metric":"design_agents_godot_elo","value":1187,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-max","source":"designarena","metric":"design_agents_godot_elo_battles","value":1213,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.5","source":"designarena","metric":"design_agents_godot_elo","value":1173,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.5","source":"designarena","metric":"design_agents_godot_elo_battles","value":1226,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.7-code","source":"designarena","metric":"design_agents_godot_elo","value":1147,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.7-code","source":"designarena","metric":"design_agents_godot_elo_battles","value":1103,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.6","source":"designarena","metric":"design_agents_godot_elo","value":1120,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.6","source":"designarena","metric":"design_agents_godot_elo_battles","value":1497,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.5-flash","source":"designarena","metric":"design_agents_godot_elo","value":1098,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.5-flash","source":"designarena","metric":"design_agents_godot_elo_battles","value":1345,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.1","source":"designarena","metric":"design_agents_godot_elo","value":1053,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.1","source":"designarena","metric":"design_agents_godot_elo_battles","value":431,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5v-turbo","source":"designarena","metric":"design_agents_godot_elo","value":957,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5v-turbo","source":"designarena","metric":"design_agents_godot_elo_battles","value":1944,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.3","source":"designarena","metric":"design_agents_godot_elo","value":914,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.3","source":"designarena","metric":"design_agents_godot_elo_battles","value":314,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5","source":"designarena","metric":"design_agents_gamedev_elo","value":1285,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5","source":"designarena","metric":"design_agents_gamedev_elo_battles","value":1428,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-sol","source":"designarena","metric":"design_agents_gamedev_elo","value":1267,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-sol","source":"designarena","metric":"design_agents_gamedev_elo_battles","value":1049,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5","source":"designarena","metric":"design_agents_gamedev_elo","value":1262,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5","source":"designarena","metric":"design_agents_gamedev_elo_battles","value":782,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k3","source":"designarena","metric":"design_agents_gamedev_elo","value":1251,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k3","source":"designarena","metric":"design_agents_gamedev_elo_battles","value":699,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.8","source":"designarena","metric":"design_agents_gamedev_elo","value":1238,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.8","source":"designarena","metric":"design_agents_gamedev_elo_battles","value":1375,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.7-flash","source":"designarena","metric":"design_agents_gamedev_elo","value":1235,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.7-flash","source":"designarena","metric":"design_agents_gamedev_elo_battles","value":4709,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5","source":"designarena","metric":"design_agents_gamedev_elo","value":1227,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5","source":"designarena","metric":"design_agents_gamedev_elo_battles","value":1405,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.6","source":"designarena","metric":"design_agents_gamedev_elo","value":1212,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.6","source":"designarena","metric":"design_agents_gamedev_elo_battles","value":219,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.2","source":"designarena","metric":"design_agents_gamedev_elo","value":1206,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.2","source":"designarena","metric":"design_agents_gamedev_elo_battles","value":853,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.5-flash","source":"designarena","metric":"design_agents_gamedev_elo","value":1180,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.5-flash","source":"designarena","metric":"design_agents_gamedev_elo_battles","value":3583,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.6-flash","source":"designarena","metric":"design_agents_gamedev_elo","value":1180,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.6-flash","source":"designarena","metric":"design_agents_gamedev_elo_battles","value":1695,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.5","source":"designarena","metric":"design_agents_gamedev_elo","value":1179,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.5","source":"designarena","metric":"design_agents_gamedev_elo_battles","value":2275,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.2","source":"designarena","metric":"design_agents_gamedev_elo","value":1179,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.2","source":"designarena","metric":"design_agents_gamedev_elo_battles","value":620,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.6","source":"designarena","metric":"design_agents_gamedev_elo","value":1177,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.6","source":"designarena","metric":"design_agents_gamedev_elo_battles","value":245,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.1","source":"designarena","metric":"design_agents_gamedev_elo","value":1164,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.1","source":"designarena","metric":"design_agents_gamedev_elo_battles","value":1497,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-max","source":"designarena","metric":"design_agents_gamedev_elo","value":1161,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-max","source":"designarena","metric":"design_agents_gamedev_elo_battles","value":711,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m3","source":"designarena","metric":"design_agents_gamedev_elo","value":1156,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m3","source":"designarena","metric":"design_agents_gamedev_elo_battles","value":514,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.6","source":"designarena","metric":"design_agents_gamedev_elo","value":1141,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.6","source":"designarena","metric":"design_agents_gamedev_elo_battles","value":2462,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.7-code","source":"designarena","metric":"design_agents_gamedev_elo","value":1130,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.7-code","source":"designarena","metric":"design_agents_gamedev_elo_battles","value":832,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-pro-preview","source":"designarena","metric":"design_agents_gamedev_elo","value":1114,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-pro-preview","source":"designarena","metric":"design_agents_gamedev_elo_battles","value":1862,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5v-turbo","source":"designarena","metric":"design_agents_gamedev_elo","value":1102,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5v-turbo","source":"designarena","metric":"design_agents_gamedev_elo_battles","value":1953,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-terra","source":"designarena","metric":"design_agents_gamedev_elo","value":1082,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-terra","source":"designarena","metric":"design_agents_gamedev_elo_battles","value":659,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.3","source":"designarena","metric":"design_agents_gamedev_elo","value":1007,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.3","source":"designarena","metric":"design_agents_gamedev_elo_battles","value":1917,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-sol","source":"designarena","metric":"design_agents_html_slides_elo","value":1286,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-sol","source":"designarena","metric":"design_agents_html_slides_elo_battles","value":451,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5","source":"designarena","metric":"design_agents_html_slides_elo","value":1277,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5","source":"designarena","metric":"design_agents_html_slides_elo_battles","value":2181,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k3","source":"designarena","metric":"design_agents_html_slides_elo","value":1256,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k3","source":"designarena","metric":"design_agents_html_slides_elo_battles","value":3960,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.8","source":"designarena","metric":"design_agents_html_slides_elo","value":1221,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.8","source":"designarena","metric":"design_agents_html_slides_elo_battles","value":3664,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5","source":"designarena","metric":"design_agents_html_slides_elo","value":1218,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5","source":"designarena","metric":"design_agents_html_slides_elo_battles","value":2104,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.7-code","source":"designarena","metric":"design_agents_html_slides_elo","value":1201,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.7-code","source":"designarena","metric":"design_agents_html_slides_elo_battles","value":1233,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.6","source":"designarena","metric":"design_agents_html_slides_elo","value":1184,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.6","source":"designarena","metric":"design_agents_html_slides_elo_battles","value":2327,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m3","source":"designarena","metric":"design_agents_html_slides_elo","value":1180,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m3","source":"designarena","metric":"design_agents_html_slides_elo_battles","value":1246,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.2","source":"designarena","metric":"design_agents_html_slides_elo","value":1175,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.2","source":"designarena","metric":"design_agents_html_slides_elo_battles","value":1881,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.1","source":"designarena","metric":"design_agents_html_slides_elo","value":1170,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.1","source":"designarena","metric":"design_agents_html_slides_elo_battles","value":3133,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-max","source":"designarena","metric":"design_agents_html_slides_elo","value":1158,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-max","source":"designarena","metric":"design_agents_html_slides_elo_battles","value":1209,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-pro-preview","source":"designarena","metric":"design_agents_html_slides_elo","value":1153,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-pro-preview","source":"designarena","metric":"design_agents_html_slides_elo_battles","value":1979,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.6-flash","source":"designarena","metric":"design_agents_html_slides_elo","value":1148,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.6-flash","source":"designarena","metric":"design_agents_html_slides_elo_battles","value":1261,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5","source":"designarena","metric":"design_agents_html_slides_elo","value":1148,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5","source":"designarena","metric":"design_agents_html_slides_elo_battles","value":366,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.5-flash","source":"designarena","metric":"design_agents_html_slides_elo","value":1142,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.5-flash","source":"designarena","metric":"design_agents_html_slides_elo_battles","value":2196,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.2","source":"designarena","metric":"design_agents_html_slides_elo","value":1135,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.2","source":"designarena","metric":"design_agents_html_slides_elo_battles","value":2091,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5v-turbo","source":"designarena","metric":"design_agents_html_slides_elo","value":1120,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5v-turbo","source":"designarena","metric":"design_agents_html_slides_elo_battles","value":2275,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-terra","source":"designarena","metric":"design_agents_html_slides_elo","value":1108,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-terra","source":"designarena","metric":"design_agents_html_slides_elo_battles","value":1014,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.5","source":"designarena","metric":"design_agents_html_slides_elo","value":1067,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.5","source":"designarena","metric":"design_agents_html_slides_elo_battles","value":2055,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.3","source":"designarena","metric":"design_agents_html_slides_elo","value":1008,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.3","source":"designarena","metric":"design_agents_html_slides_elo_battles","value":1937,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5.1","source":"designarena","metric":"design_agents_pptx_slides_elo","value":1328,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5.1","source":"designarena","metric":"design_agents_pptx_slides_elo_battles","value":768,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5","source":"designarena","metric":"design_agents_pptx_slides_elo","value":1295,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-fable-5","source":"designarena","metric":"design_agents_pptx_slides_elo_battles","value":1914,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k3","source":"designarena","metric":"design_agents_pptx_slides_elo","value":1273,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k3","source":"designarena","metric":"design_agents_pptx_slides_elo_battles","value":3281,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5","source":"designarena","metric":"design_agents_pptx_slides_elo","value":1266,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5","source":"designarena","metric":"design_agents_pptx_slides_elo_battles","value":605,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.8-max-0902","source":"designarena","metric":"design_agents_pptx_slides_elo","value":1256,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.8-max-0902","source":"designarena","metric":"design_agents_pptx_slides_elo_battles","value":384,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.3","source":"designarena","metric":"design_agents_pptx_slides_elo","value":1255,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.3","source":"designarena","metric":"design_agents_pptx_slides_elo_battles","value":248,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-astra","source":"designarena","metric":"design_agents_pptx_slides_elo","value":1245,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6-astra","source":"designarena","metric":"design_agents_pptx_slides_elo_battles","value":804,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.3","source":"designarena","metric":"design_agents_pptx_slides_elo","value":1244,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.3","source":"designarena","metric":"design_agents_pptx_slides_elo_battles","value":3771,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-sol","source":"designarena","metric":"design_agents_pptx_slides_elo","value":1240,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-sol","source":"designarena","metric":"design_agents_pptx_slides_elo_battles","value":1215,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.8","source":"designarena","metric":"design_agents_pptx_slides_elo","value":1227,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-4.8","source":"designarena","metric":"design_agents_pptx_slides_elo_battles","value":1493,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5","source":"designarena","metric":"design_agents_pptx_slides_elo","value":1216,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5","source":"designarena","metric":"design_agents_pptx_slides_elo_battles","value":2123,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m3","source":"designarena","metric":"design_agents_pptx_slides_elo","value":1205,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m3","source":"designarena","metric":"design_agents_pptx_slides_elo_battles","value":1058,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.2","source":"designarena","metric":"design_agents_pptx_slides_elo","value":1198,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.2","source":"designarena","metric":"design_agents_pptx_slides_elo_battles","value":1752,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.2","source":"designarena","metric":"design_agents_pptx_slides_elo","value":1195,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.2","source":"designarena","metric":"design_agents_pptx_slides_elo_battles","value":1170,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-max","source":"designarena","metric":"design_agents_pptx_slides_elo","value":1195,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.7-max","source":"designarena","metric":"design_agents_pptx_slides_elo_battles","value":949,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.1","source":"designarena","metric":"design_agents_pptx_slides_elo","value":1189,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.1","source":"designarena","metric":"design_agents_pptx_slides_elo_battles","value":1933,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.8-flash","source":"designarena","metric":"design_agents_pptx_slides_elo","value":1179,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.8-flash","source":"designarena","metric":"design_agents_pptx_slides_elo_battles","value":819,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.5-flash","source":"designarena","metric":"design_agents_pptx_slides_elo","value":1178,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.5-flash","source":"designarena","metric":"design_agents_pptx_slides_elo_battles","value":4040,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.7-code","source":"designarena","metric":"design_agents_pptx_slides_elo","value":1154,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.7-code","source":"designarena","metric":"design_agents_pptx_slides_elo_battles","value":836,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5v-turbo","source":"designarena","metric":"design_agents_pptx_slides_elo","value":1151,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5v-turbo","source":"designarena","metric":"design_agents_pptx_slides_elo_battles","value":775,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.6-flash","source":"designarena","metric":"design_agents_pptx_slides_elo","value":1145,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.6-flash","source":"designarena","metric":"design_agents_pptx_slides_elo_battles","value":855,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-terra","source":"designarena","metric":"design_agents_pptx_slides_elo","value":1130,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.6-terra","source":"designarena","metric":"design_agents_pptx_slides_elo_battles","value":870,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.6","source":"designarena","metric":"design_agents_pptx_slides_elo","value":1128,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.6","source":"designarena","metric":"design_agents_pptx_slides_elo_battles","value":1728,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.5","source":"designarena","metric":"design_agents_pptx_slides_elo","value":1108,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.5","source":"designarena","metric":"design_agents_pptx_slides_elo_battles","value":1237,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-pro-preview","source":"designarena","metric":"design_agents_pptx_slides_elo","value":1063,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-pro-preview","source":"designarena","metric":"design_agents_pptx_slides_elo_battles","value":1341,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.3","source":"designarena","metric":"design_agents_pptx_slides_elo","value":1011,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.3","source":"designarena","metric":"design_agents_pptx_slides_elo_battles","value":896,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.1","source":"designarena","metric":"design_agents_spreadsheet_elo","value":1315,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.1","source":"designarena","metric":"design_agents_spreadsheet_elo_battles","value":29,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.6","source":"designarena","metric":"design_agents_spreadsheet_elo","value":1276,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.6","source":"designarena","metric":"design_agents_spreadsheet_elo_battles","value":31,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m3","source":"designarena","metric":"design_agents_spreadsheet_elo","value":1250,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m3","source":"designarena","metric":"design_agents_spreadsheet_elo_battles","value":35,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.7-flash","source":"designarena","metric":"design_agents_spreadsheet_elo","value":1157,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.7-flash","source":"designarena","metric":"design_agents_spreadsheet_elo_battles","value":22,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.6-flash","source":"designarena","metric":"design_agents_spreadsheet_elo","value":1156,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.6-flash","source":"designarena","metric":"design_agents_spreadsheet_elo_battles","value":36,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5","source":"designarena","metric":"design_agents_spreadsheet_elo","value":1138,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-5","source":"designarena","metric":"design_agents_spreadsheet_elo_battles","value":42,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.8-flash","source":"designarena","metric":"design_agents_spreadsheet_elo","value":1138,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.8-flash","source":"designarena","metric":"design_agents_spreadsheet_elo_battles","value":90,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.8-max-0902","source":"designarena","metric":"design_agents_spreadsheet_elo","value":1015,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3.8-max-0902","source":"designarena","metric":"design_agents_spreadsheet_elo_battles","value":34,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-nano-banana-2.1","source":"designarena","metric":"design_image_elo","value":1291,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-nano-banana-2.1","source":"designarena","metric":"design_image_elo_battles","value":2945,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-flash-image-preview","source":"designarena","metric":"design_image_elo","value":1269,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-flash-image-preview","source":"designarena","metric":"design_image_elo_battles","value":91596,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-flash-lite-image","source":"designarena","metric":"design_image_elo","value":1239,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-flash-lite-image","source":"designarena","metric":"design_image_elo_battles","value":155048,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3-pro-image-preview","source":"designarena","metric":"design_image_elo","value":1216,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3-pro-image-preview","source":"designarena","metric":"design_image_elo_battles","value":5033,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-2.5-flash-image","source":"designarena","metric":"design_image_elo","value":1179,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-2.5-flash-image","source":"designarena","metric":"design_image_elo_battles","value":190860,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-nano-banana-2.1","source":"designarena","metric":"design_graphic_design_elo","value":1336,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-nano-banana-2.1","source":"designarena","metric":"design_graphic_design_elo_battles","value":524,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-flash-image-preview","source":"designarena","metric":"design_graphic_design_elo","value":1249,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-flash-image-preview","source":"designarena","metric":"design_graphic_design_elo_battles","value":11632,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-flash-lite-image","source":"designarena","metric":"design_graphic_design_elo","value":1249,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-flash-lite-image","source":"designarena","metric":"design_graphic_design_elo_battles","value":27294,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3-pro-image-preview","source":"designarena","metric":"design_graphic_design_elo","value":1226,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3-pro-image-preview","source":"designarena","metric":"design_graphic_design_elo_battles","value":1142,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-2.5-flash-image","source":"designarena","metric":"design_graphic_design_elo","value":1151,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-2.5-flash-image","source":"designarena","metric":"design_graphic_design_elo_battles","value":25648,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-nano-banana-2.1","source":"designarena","metric":"design_logo_elo","value":1278,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-nano-banana-2.1","source":"designarena","metric":"design_logo_elo_battles","value":1020,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-flash-image-preview","source":"designarena","metric":"design_logo_elo","value":1248,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-flash-image-preview","source":"designarena","metric":"design_logo_elo_battles","value":21681,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-flash-lite-image","source":"designarena","metric":"design_logo_elo","value":1214,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-flash-lite-image","source":"designarena","metric":"design_logo_elo_battles","value":53145,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3-pro-image-preview","source":"designarena","metric":"design_logo_elo","value":1181,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3-pro-image-preview","source":"designarena","metric":"design_logo_elo_battles","value":1069,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-2.5-flash-image","source":"designarena","metric":"design_logo_elo","value":1169,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-2.5-flash-image","source":"designarena","metric":"design_logo_elo_battles","value":64804,"unit":"count","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"reflection/beam-1.0-501b-a23b","source":"designarena","metric":"design_gamedev_elo","value":1232,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-wonder","source":"designarena","metric":"design_dataviz_elo","value":1330,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-6.1-sol","source":"designarena","metric":"design_dataviz_elo","value":1321,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"designarena","metric":"design_agents_webapps_elo","value":1289,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"designarena","metric":"design_3d_elo","value":1331,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"designarena","metric":"design_code_overall_elo","value":1317,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"designarena","metric":"design_dataviz_elo","value":1337,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"designarena","metric":"design_gamedev_elo","value":1313,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"designarena","metric":"design_ui_elo","value":1340,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"xiaomi/mimo-v2.6-pro","source":"designarena","metric":"design_website_elo","value":1308,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.3","source":"designarena","metric":"design_agents_godot_elo","value":1241,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.3-flash","source":"designarena","metric":"design_3d_elo","value":1316,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.3-flash","source":"designarena","metric":"design_ascii_art_elo","value":1269,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.3-flash","source":"designarena","metric":"design_code_overall_elo","value":1282,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.3-flash","source":"designarena","metric":"design_dataviz_elo","value":1260,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.3-flash","source":"designarena","metric":"design_gamedev_elo","value":1279,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.3-flash","source":"designarena","metric":"design_svg_elo","value":1285,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.3-flash","source":"designarena","metric":"design_ui_elo","value":1317,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.3-flash","source":"designarena","metric":"design_website_elo","value":1272,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.3","source":"designarena","metric":"design_3d_elo","value":1334,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.3","source":"designarena","metric":"design_ascii_art_elo","value":1211,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.3","source":"designarena","metric":"design_code_overall_elo","value":1304,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.3","source":"designarena","metric":"design_dataviz_elo","value":1258,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.3","source":"designarena","metric":"design_gamedev_elo","value":1312,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.3","source":"designarena","metric":"design_svg_elo","value":1293,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.3","source":"designarena","metric":"design_ui_elo","value":1314,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.3","source":"designarena","metric":"design_website_elo","value":1295,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.3","source":"designarena","metric":"design_agents_html_slides_elo","value":1189,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.6","source":"designarena","metric":"design_agents_gamedev_elo","value":1208,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.6","source":"designarena","metric":"design_agents_android_elo","value":1303,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.6","source":"designarena","metric":"design_agents_fullstack_elo","value":1264,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.6","source":"designarena","metric":"design_agents_godot_elo","value":1276,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.6","source":"designarena","metric":"design_agents_html_slides_elo","value":1249,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.6","source":"designarena","metric":"design_agents_mobileapps_elo","value":1234,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.6","source":"designarena","metric":"design_agents_pptx_slides_elo","value":1241,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.6","source":"designarena","metric":"design_agents_webapps_elo","value":1247,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.6","source":"designarena","metric":"design_3d_elo","value":1277,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.6","source":"designarena","metric":"design_ascii_art_elo","value":1282,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.6","source":"designarena","metric":"design_code_overall_elo","value":1292,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.6","source":"designarena","metric":"design_dataviz_elo","value":1283,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.6","source":"designarena","metric":"design_gamedev_elo","value":1296,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.6","source":"designarena","metric":"design_svg_elo","value":1239,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.6","source":"designarena","metric":"design_ui_elo","value":1293,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.6","source":"designarena","metric":"design_website_elo","value":1289,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-opus-5","source":"designarena","metric":"design_agents_mobileapps_elo","value":1348,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.1","source":"designarena","metric":"design_agents_gamedev_elo","value":1183,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.1","source":"designarena","metric":"design_agents_android_elo","value":1190,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.1","source":"designarena","metric":"design_agents_fullstack_elo","value":1199,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.1","source":"designarena","metric":"design_agents_godot_elo","value":1103,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.1","source":"designarena","metric":"design_agents_html_slides_elo","value":1194,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.1","source":"designarena","metric":"design_agents_mobileapps_elo","value":1174,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.1","source":"designarena","metric":"design_agents_pptx_slides_elo","value":1156,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.1","source":"designarena","metric":"design_agents_spreadsheet_elo","value":1179,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.1","source":"designarena","metric":"design_agents_webapps_elo","value":1206,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.1","source":"designarena","metric":"design_3d_elo","value":1260,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.1","source":"designarena","metric":"design_ascii_art_elo","value":1270,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.1","source":"designarena","metric":"design_code_overall_elo","value":1277,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.1","source":"designarena","metric":"design_dataviz_elo","value":1268,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.1","source":"designarena","metric":"design_gamedev_elo","value":1269,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.1","source":"designarena","metric":"design_svg_elo","value":1234,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.1","source":"designarena","metric":"design_ui_elo","value":1290,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta/muse-spark-1.1","source":"designarena","metric":"design_website_elo","value":1270,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.5","source":"designarena","metric":"design_agents_gamedev_elo","value":1235,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.5","source":"designarena","metric":"design_agents_android_elo","value":1249,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.5","source":"designarena","metric":"design_agents_fullstack_elo","value":1249,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.5","source":"designarena","metric":"design_agents_godot_elo","value":1229,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.5","source":"designarena","metric":"design_agents_html_slides_elo","value":1204,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.5","source":"designarena","metric":"design_agents_mobileapps_elo","value":1219,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.5","source":"designarena","metric":"design_agents_pptx_slides_elo","value":1232,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.5","source":"designarena","metric":"design_agents_webapps_elo","value":1217,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.5","source":"designarena","metric":"design_3d_elo","value":1258,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.5","source":"designarena","metric":"design_ascii_art_elo","value":1258,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.5","source":"designarena","metric":"design_code_overall_elo","value":1276,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.5","source":"designarena","metric":"design_dataviz_elo","value":1267,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.5","source":"designarena","metric":"design_gamedev_elo","value":1263,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.5","source":"designarena","metric":"design_svg_elo","value":1216,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.5","source":"designarena","metric":"design_ui_elo","value":1279,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.5","source":"designarena","metric":"design_website_elo","value":1281,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.2","source":"designarena","metric":"design_agents_godot_elo","value":1142,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-pro","source":"designarena","metric":"design_agents_fullstack_elo","value":948,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-pro","source":"designarena","metric":"design_agents_godot_elo","value":1059,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v4-pro","source":"designarena","metric":"design_agents_webapps_elo","value":1000,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.6","source":"designarena","metric":"design_agents_webapps_elo","value":1268,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.1","source":"designarena","metric":"design_3d_elo","value":1336,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.1","source":"designarena","metric":"design_ascii_art_elo","value":1142,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.1","source":"designarena","metric":"design_code_overall_elo","value":1269,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.1","source":"designarena","metric":"design_dataviz_elo","value":1366,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.1","source":"designarena","metric":"design_gamedev_elo","value":1264,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.1","source":"designarena","metric":"design_svg_elo","value":1217,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.1","source":"designarena","metric":"design_ui_elo","value":1292,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5.1","source":"designarena","metric":"design_website_elo","value":1290,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5v-turbo","source":"designarena","metric":"design_agents_android_elo","value":1267,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.20","source":"designarena","metric":"design_agents_android_elo","value":1060,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.20","source":"designarena","metric":"design_agents_fullstack_elo","value":1054,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.20","source":"designarena","metric":"design_agents_godot_elo","value":1089,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.20","source":"designarena","metric":"design_agents_html_slides_elo","value":1180,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.20","source":"designarena","metric":"design_agents_mobileapps_elo","value":1089,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.20","source":"designarena","metric":"design_agents_webapps_elo","value":1143,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.20","source":"designarena","metric":"design_3d_elo","value":1194,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.20","source":"designarena","metric":"design_ascii_art_elo","value":1175,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.20","source":"designarena","metric":"design_code_overall_elo","value":1222,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.20","source":"designarena","metric":"design_dataviz_elo","value":1217,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.20","source":"designarena","metric":"design_gamedev_elo","value":1192,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.20","source":"designarena","metric":"design_svg_elo","value":1164,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.20","source":"designarena","metric":"design_ui_elo","value":1199,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"x-ai/grok-4.20","source":"designarena","metric":"design_website_elo","value":1231,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2.7","source":"designarena","metric":"design_3d_elo","value":1195,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2.7","source":"designarena","metric":"design_ascii_art_elo","value":1138,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2.7","source":"designarena","metric":"design_code_overall_elo","value":1234,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2.7","source":"designarena","metric":"design_dataviz_elo","value":1234,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2.7","source":"designarena","metric":"design_gamedev_elo","value":1210,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2.7","source":"designarena","metric":"design_svg_elo","value":1136,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2.7","source":"designarena","metric":"design_ui_elo","value":1210,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2.7","source":"designarena","metric":"design_website_elo","value":1243,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.4","source":"designarena","metric":"design_agents_godot_elo","value":1135,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.3-codex","source":"designarena","metric":"design_agents_android_elo","value":1084,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.3-codex","source":"designarena","metric":"design_agents_godot_elo","value":1124,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3.1-pro-preview","source":"designarena","metric":"design_agents_godot_elo","value":1236,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"anthropic/claude-sonnet-4.6","source":"designarena","metric":"design_agents_godot_elo","value":1226,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2.5","source":"designarena","metric":"design_3d_elo","value":1170,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2.5","source":"designarena","metric":"design_code_overall_elo","value":1207,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2.5","source":"designarena","metric":"design_dataviz_elo","value":1171,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2.5","source":"designarena","metric":"design_gamedev_elo","value":1176,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2.5","source":"designarena","metric":"design_svg_elo","value":1147,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2.5","source":"designarena","metric":"design_ui_elo","value":1174,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2.5","source":"designarena","metric":"design_website_elo","value":1222,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-5","source":"designarena","metric":"design_agents_godot_elo","value":1144,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2.5","source":"designarena","metric":"design_agents_godot_elo","value":1219,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.2-codex","source":"designarena","metric":"design_agents_android_elo","value":1176,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.2-codex","source":"designarena","metric":"design_agents_godot_elo","value":1142,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.7","source":"designarena","metric":"design_agents_godot_elo","value":1058,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3-flash-preview","source":"designarena","metric":"design_agents_godot_elo","value":1161,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-3-flash-preview","source":"designarena","metric":"design_agents_pptx_slides_elo","value":1036,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.2","source":"designarena","metric":"design_website_elo","value":1196,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.2","source":"designarena","metric":"design_agents_godot_elo","value":1142,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.2","source":"designarena","metric":"design_3d_elo","value":1079,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.2","source":"designarena","metric":"design_code_overall_elo","value":1171,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.2","source":"designarena","metric":"design_dataviz_elo","value":1202,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.2","source":"designarena","metric":"design_gamedev_elo","value":1196,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.2","source":"designarena","metric":"design_ui_elo","value":1190,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.2","source":"designarena","metric":"design_ascii_art_elo","value":1153,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.2","source":"designarena","metric":"design_svg_elo","value":1137,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1-codex","source":"designarena","metric":"design_agents_fullstack_elo","value":1086,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5.1-codex","source":"designarena","metric":"design_agents_mobileapps_elo","value":1191,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2","source":"designarena","metric":"design_3d_elo","value":1098,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2","source":"designarena","metric":"design_code_overall_elo","value":1135,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2","source":"designarena","metric":"design_dataviz_elo","value":1140,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2","source":"designarena","metric":"design_gamedev_elo","value":1119,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2","source":"designarena","metric":"design_svg_elo","value":1098,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2","source":"designarena","metric":"design_ui_elo","value":1136,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"minimax/minimax-m2","source":"designarena","metric":"design_website_elo","value":1144,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5-image-mini","source":"designarena","metric":"design_graphic_design_elo","value":1165,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5-image-mini","source":"designarena","metric":"design_image_elo","value":1184,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5-image-mini","source":"designarena","metric":"design_logo_elo","value":1208,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5-image","source":"designarena","metric":"design_graphic_design_elo","value":1172,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5-image","source":"designarena","metric":"design_image_elo","value":1191,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-5-image","source":"designarena","metric":"design_logo_elo","value":1202,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"z-ai/glm-4.6","source":"designarena","metric":"design_agents_godot_elo","value":1180,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"designarena","metric":"design_3d_elo","value":1141,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"designarena","metric":"design_code_overall_elo","value":1177,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"designarena","metric":"design_dataviz_elo","value":1167,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"designarena","metric":"design_gamedev_elo","value":1130,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"designarena","metric":"design_svg_elo","value":1063,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"designarena","metric":"design_ui_elo","value":1182,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-v3.1-terminus","source":"designarena","metric":"design_website_elo","value":1188,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2-0905","source":"designarena","metric":"design_code_overall_elo","value":1098,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-chat-v3.1","source":"designarena","metric":"design_3d_elo","value":1077,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-chat-v3.1","source":"designarena","metric":"design_code_overall_elo","value":1113,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-chat-v3.1","source":"designarena","metric":"design_dataviz_elo","value":1095,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-chat-v3.1","source":"designarena","metric":"design_gamedev_elo","value":1085,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-chat-v3.1","source":"designarena","metric":"design_svg_elo","value":965,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-chat-v3.1","source":"designarena","metric":"design_ui_elo","value":1085,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"deepseek/deepseek-chat-v3.1","source":"designarena","metric":"design_website_elo","value":1124,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-oss-20b","source":"designarena","metric":"design_dataviz_elo","value":933,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-coder-30b-a3b-instruct","source":"designarena","metric":"design_dataviz_elo","value":1085,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-235b-a22b-thinking-2507","source":"designarena","metric":"design_dataviz_elo","value":950,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-coder","source":"designarena","metric":"design_dataviz_elo","value":1084,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"moonshotai/kimi-k2","source":"designarena","metric":"design_dataviz_elo","value":1018,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-small-3.2-24b-instruct","source":"designarena","metric":"design_code_overall_elo","value":907,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-small-3.2-24b-instruct","source":"designarena","metric":"design_dataviz_elo","value":929,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-small-3.2-24b-instruct","source":"designarena","metric":"design_gamedev_elo","value":888,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-small-3.2-24b-instruct","source":"designarena","metric":"design_ui_elo","value":908,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"mistralai/mistral-small-3.2-24b-instruct","source":"designarena","metric":"design_website_elo","value":897,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"google/gemini-2.5-flash","source":"designarena","metric":"design_svg_elo","value":1018,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"qwen/qwen3-30b-a3b","source":"designarena","metric":"design_dataviz_elo","value":967,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/o3","source":"designarena","metric":"design_code_overall_elo","value":1021,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/o3","source":"designarena","metric":"design_dataviz_elo","value":1200,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/o3","source":"designarena","metric":"design_gamedev_elo","value":1034,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/o3","source":"designarena","metric":"design_ui_elo","value":1018,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/o3","source":"designarena","metric":"design_website_elo","value":1036,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/o4-mini","source":"designarena","metric":"design_3d_elo","value":854,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/o4-mini","source":"designarena","metric":"design_code_overall_elo","value":977,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/o4-mini","source":"designarena","metric":"design_dataviz_elo","value":990,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/o4-mini","source":"designarena","metric":"design_gamedev_elo","value":1004,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/o4-mini","source":"designarena","metric":"design_ui_elo","value":983,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/o4-mini","source":"designarena","metric":"design_website_elo","value":985,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4.1","source":"designarena","metric":"design_dataviz_elo","value":1104,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4.1-mini","source":"designarena","metric":"design_dataviz_elo","value":1034,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta-llama/llama-4-maverick","source":"designarena","metric":"design_dataviz_elo","value":882,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"meta-llama/llama-4-scout","source":"designarena","metric":"design_dataviz_elo","value":896,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"},{"modelId":"openai/gpt-4o","source":"designarena","metric":"design_dataviz_elo","value":858,"unit":"elo","observedAt":"2026-10-20","sourceUrl":"https://www.designarena.ai/leaderboard"}],"sources":[{"id":"openrouter","label":"OpenRouter","homepage":"https://openrouter.ai/","fetchedAt":"2026-10-20","rowCount":356},{"id":"artificialanalysis","label":"Artificial Analysis (via OpenRouter)","homepage":"https://artificialanalysis.ai/","fetchedAt":"2026-10-20","rowCount":213},{"id":"aider","label":"Aider polyglot leaderboard","homepage":"https://aider.chat/docs/leaderboards/","fetchedAt":"2026-10-20","rowCount":22},{"id":"ale-bench","label":"ALE-Bench (Sakana AI)","homepage":"https://sakanaai.github.io/ALE-Bench-Leaderboard/","fetchedAt":"2026-10-20","rowCount":104},{"id":"vals-aime","label":"AIME (Vals AI)","homepage":"https://www.vals.ai/benchmarks/aime","fetchedAt":"2026-10-20","rowCount":54,"updatedAt":"2026-04-16"},{"id":"lmarena","label":"LMArena WebDev","homepage":"https://lmarena.ai/leaderboard/webdev","fetchedAt":"2026-10-20","rowCount":101},{"id":"swebench","label":"SWE-bench (swebench.com)","homepage":"https://www.swebench.com/","fetchedAt":"2026-10-20","rowCount":38},{"id":"vals-gpqa","label":"GPQA (Vals AI)","homepage":"https://www.vals.ai/benchmarks/gpqa","fetchedAt":"2026-10-20","rowCount":91,"updatedAt":"2026-09-01"},{"id":"livebench","label":"LiveBench","homepage":"https://livebench.ai/","fetchedAt":"2026-10-20","rowCount":43,"updatedAt":"2026-10-14"},{"id":"vals-mmlu-pro","label":"MMLU Pro (Vals AI)","homepage":"https://www.vals.ai/benchmarks/mmlu_pro","fetchedAt":"2026-10-20","rowCount":92,"updatedAt":"2026-09-01"},{"id":"valsai","label":"Vals Index","homepage":"https://www.vals.ai/benchmarks/vals_index","fetchedAt":"2026-10-20","rowCount":20,"updatedAt":"2026-10-19"},{"id":"aa-api","label":"Artificial Analysis","homepage":"https://artificialanalysis.ai/","fetchedAt":"2026-10-20","rowCount":195},{"id":"openrouter-speed","label":"OpenRouter (provider speed)","homepage":"https://openrouter.ai/","fetchedAt":"2026-10-20","rowCount":175},{"id":"huggingface","label":"Hugging Face","homepage":"https://huggingface.co/models","fetchedAt":"2026-10-20","rowCount":151},{"id":"epoch","label":"Epoch AI benchmarking hub","homepage":"https://epoch.ai/benchmarks","fetchedAt":"2026-10-20","rowCount":198},{"id":"vals-more","label":"Vals AI boards","homepage":"https://www.vals.ai/benchmarks","fetchedAt":"2026-10-20","rowCount":132},{"id":"arena","label":"LMArena (Hugging Face dataset)","homepage":"https://lmarena.ai/leaderboard","fetchedAt":"2026-10-20","rowCount":169},{"id":"designarena","label":"Design Arena","homepage":"https://www.designarena.ai/","fetchedAt":"2026-10-20","rowCount":141}],"generatedAt":"2026-10-20T04:16:11.583Z"}